{"as_of":"2026-08-13T16:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6e63c741606dc9c29088e68c9c769ebd1b16e919cd38a687d6e59a39d1f4a778","coverage":[{"denominator":66,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":66,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T01:14:59.819915Z","state":"measured"},{"denominator":66,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":66,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.25894/citation-record","integrity":"/paper/2607.25894/integrity","json":"/paper/2607.25894/citation-record.json","paper":"/paper/2607.25894"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:52.873343Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:52.873343Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:2475faf4a93e743fa5268a8221e8799c7a577ae98331da1c8b79ba2217f22a4c","observation_id":"3313d70c-4eef-439c-b98a-48e64c51b632","resolution":{"observed_at":"2026-08-01T01:14:52.873343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:52.960498Z","title":"High- resolution image synthesis with latent diffusion models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:52.960498Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:55d9b09782ef2a511726134d546095ef155abc999ae16afbddc7e32f729145e5","observation_id":"b05f96a8-bae2-46c5-9076-49cc25fdf799","resolution":{"observed_at":"2026-08-01T01:14:52.960498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:53.077347Z","title":"Collaborative diffusion for multi-modal face generation and editing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:53.077347Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:e253f15837a3429d8e792e22273419d03a62ff5babda435096154a3aed7140bf","observation_id":"62250858-20d3-48c7-b20a-45b095504791","resolution":{"observed_at":"2026-08-01T01:14:53.077347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:53.217115Z","title":"Defensive adversarial captcha: A semantics- driven framework for natural adversarial example generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:53.217115Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:c7c45a98f5178bbcca78a3f6594536e1489ac6efd3ac57b645530d49eca5c3cd","observation_id":"309b3e8b-b371-4412-ab77-4a934befe55c","resolution":{"observed_at":"2026-08-01T01:14:53.217115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:53.354334Z","title":"State-aware perturbation optimization for robust deep reinforcement learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:53.354334Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:fc110443504803f81f2762b66dca104e39f65211d758daa0ba1b52829f7c9e16","observation_id":"9a8e2f0f-9f27-4e3c-ab81-80ad36c641f3","resolution":{"observed_at":"2026-08-01T01:14:53.354334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:53.503852Z","title":"LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:53.503852Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:6ff71a15374780879534240d9719fde263efa972a2bf399926e1dec5b7cd1a5d","observation_id":"2c05ceaf-c0c0-4ed6-b58d-b6dd970832c6","resolution":{"observed_at":"2026-08-01T01:14:53.503852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:53.651950Z","title":"A deep learning approach to universal image manipulation detection using a new convolutional layer,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:53.651950Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:dbb467804e54ba869be162e05d7a4c3c5f6e12ebbce21bd50fbaaa27ca9199d5","observation_id":"c0041a79-dc1f-4535-a9c5-1de2437608ea","resolution":{"observed_at":"2026-08-01T01:14:53.651950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:53.810930Z","title":"Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Lan- guage Models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:53.810930Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:8ca69d6bbd0b60a5cf44063f75745db779b3b0be92ca74ac300888c7304e16e3","observation_id":"5fa34824-cd88-4e5f-9ac4-fb40e1661a1f","resolution":{"observed_at":"2026-08-01T01:14:53.810930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:53.958253Z","title":"CNN- generated images are surprisingly easy to spot... for now,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:53.958253Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:de6ad1f52249834d31a821adcd50163fb23eb06f891353ce27c2ad2e15a3df15","observation_id":"aabe1403-1485-4a48-964e-59a0e96db907","resolution":{"observed_at":"2026-08-01T01:14:53.958253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:54.128290Z","title":"SatSense: Multi-Satellite Collaborative Framework for Spectrum Sensing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:54.128290Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:e1829f42f9808a3829d66f129f80eec96149097c781b330635e731d10d81fd70","observation_id":"8410db36-1775-45e8-98d8-57d27697aa75","resolution":{"observed_at":"2026-08-01T01:14:54.128290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:54.284321Z","title":"SUMS: Sniffing Unknown Multiband Signals under Low Sampling Rates,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:54.284321Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:6cc087d8ead11787c809415f541681b9d3f7b67193ceeb0e9847afc7a4353ec9","observation_id":"0d47eb99-20ea-479c-bd1f-c70287b9e8ff","resolution":{"observed_at":"2026-08-01T01:14:54.284321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:54.406413Z","title":"Efficient Parallel Split Learning over Resource-Constrained Wireless Edge Networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:54.406413Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:2d47960c9d65c98ec6ad45adc650c71d72d723670b19578a10594dadefbdc5c0","observation_id":"97f70a76-038f-41e6-8dfa-7e1b206fac39","resolution":{"observed_at":"2026-08-01T01:14:54.406413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:54.570527Z","title":"Towards universal fake image detec- tors that generalize across generative models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:54.570527Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:e0aedd901dd399e06a71911c5333ab5c3c5463d02077f2d534f0a0084259950d","observation_id":"898a967a-fb71-4f61-b8a4-07a9957c6dc9","resolution":{"observed_at":"2026-08-01T01:14:54.570527Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:54.783662Z","title":"Unionformer: Unified-learning transformer with multi-view representation for im- age manipulation detection and localization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:54.783662Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:c3b16dc22e3c87d47fc754621f2781550c2113d0272d3cc9d5cc7d0214976fc6","observation_id":"445952a6-a66e-4de9-8b9d-1bcb815ef093","resolution":{"observed_at":"2026-08-01T01:14:54.783662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:54.908748Z","title":"Gapsl: A gradient-aligned parallel split learning on heterogeneous data,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:54.908748Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:42c93fbff42af2763d6c323defdd5c837f16a10ac8c39406271caedd7afa6374","observation_id":"e5361bb0-0306-4fcd-bae4-4c1c49eb955a","resolution":{"observed_at":"2026-08-01T01:14:54.908748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:55.029329Z","title":"Hfedmoe: Resource-aware heterogeneous federated learning with mixture-of-experts,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:55.029329Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:c02fdc1342d58d80afd5e7fbef56046e4c0c46840e13713a87df677790b41cea","observation_id":"c2f55e32-437e-4b8b-8aad-e09b2ddb0049","resolution":{"observed_at":"2026-08-01T01:14:55.029329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:55.154845Z","title":"Thinking in frequency: Face forgery detection by mining frequency-aware clues,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:55.154845Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:8a4a9755af2bdaeea7e47f4c20315729dbf5b723c02a5a5bb639cbbf253f4e0f","observation_id":"e73113ac-7fba-4233-970c-ceee31cb0a02","resolution":{"observed_at":"2026-08-01T01:14:55.154845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:55.268181Z","title":"Rethinking the up- sampling operations in CNN-based generative network for generalizable 13 deepfake detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:55.268181Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:87bb1971914ff11ed053915c51491250d53a312d37e3431e8f762f085b87eed7","observation_id":"71bc1562-92f1-4670-a012-ddaa1f83bf6f","resolution":{"observed_at":"2026-08-01T01:14:55.268181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:55.394580Z","title":"Dire for diffusion-generated image detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:55.394580Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:c8fac3f91026401e49d2027077f2720a6f656376f21a4299ad7a6f0b071f5442","observation_id":"8b184278-f750-4358-a91b-6b7d1c3f3994","resolution":{"observed_at":"2026-08-01T01:14:55.394580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:55.523838Z","title":"LaRE 2: Latent reconstruction error based method for diffusion-generated image detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:55.523838Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:6d6833ba71fe1fbce1bb902709fb6f1a6da22ad8d335bd371d93f91a216549c3","observation_id":"1b736b46-b64b-4b64-8a03-48977e00dde6","resolution":{"observed_at":"2026-08-01T01:14:55.523838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.00622","last_updated":"2020-04-01T17:59:59Z","snapshot_observed_at":"2026-08-12T17:33:17.750812Z","submitted_at":"2020-04-01T17:59:59Z","title":"Evading Deepfake-Image Detectors with White- and Black-Box Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.00622","snapshot_observed_at":"2026-08-01T01:14:55.635387Z","title":"Evading Deepfake-image detectors with White- and Black-Box Attacks,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:55.635387Z"},"links":{"cited_paper":"/paper/2004.00622","citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:7c3e1d62f4278474238493efeed41dce876b179df8d2374a08bf3720be83dedd","observation_id":"ff0614d9-f15c-4835-9de3-f1006392ce91","resolution":{"observed_at":"2026-08-01T01:14:55.635387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:55.748895Z","title":"Vulnerabilities in AI-generated image detection: The challenge of adversarial attacks,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:55.748895Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:6637cbd4c8c2734c7fd8a56705b7727efc70903243eef66e282a916c14eb13c6","observation_id":"9e3f7d44-2a56-4d03-9ac6-a972cd2cc514","resolution":{"observed_at":"2026-08-01T01:14:55.748895Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:55.875282Z","title":"Take fake as real: Realistic-like robust black-box adversarial attack to evade AIGC detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:55.875282Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:7947578418c956f416ef9737d34f4f0a615562c08db049b2fdb1bccf4425e1df","observation_id":"28b7b9b7-9070-48f1-a519-ad5cfd4733aa","resolution":{"observed_at":"2026-08-01T01:14:55.875282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.018537Z","title":"StealthDif- fusion: Towards evading diffusion forensic detection through diffusion model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.018537Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:edc8c5a364d79e5de9ca80c7dbdd211c07b9cbb3ea7b16879a86cfccab33fad1","observation_id":"cdb313c7-e367-4ea2-b5a7-9437f2e4c6e9","resolution":{"observed_at":"2026-08-01T01:14:56.018537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.188146Z","title":"Adversarial diffusion model: Generating high quality and undetectable images from scratch,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.188146Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:1fa9f6c8b703b92db89779cefb034478913ecd95a4a1c950873c86cfc8221fdf","observation_id":"7ed8b706-8361-4088-91a6-29c32bf7919d","resolution":{"observed_at":"2026-08-01T01:14:56.188146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10196","last_updated":"2018-02-26T15:33:34Z","snapshot_observed_at":"2026-07-06T06:06:26.276752Z","submitted_at":"2017-10-27T15:28:35Z","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10196","snapshot_observed_at":"2026-08-01T01:14:56.344873Z","title":"Progressive growing of GANs for improved quality, stability, and variation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.344873Z"},"links":{"cited_paper":"/paper/1710.10196","citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:bb2034c40787e278d1fb617393cc180881d752d5b292cd3326574b9947cb3bfb","observation_id":"d8932938-410f-4f37-ac45-81fba6f5ef6b","resolution":{"observed_at":"2026-08-01T01:14:56.344873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.446594Z","title":"A style-based generator architecture for generative adversarial networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.446594Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:a0d400d4f9eb107067aa441b38ddc7bc494f8028bd8eb333d9e0340f3eaac373","observation_id":"9eb541a9-128c-4983-a9df-cc3277c7880c","resolution":{"observed_at":"2026-08-01T01:14:56.446594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.594329Z","title":"Channel Power Gain Estimation for Terahertz Vehicle-to-Infrastructure Networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.594329Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:ebb279ef08986225d3e06631605d194b58e8d83a219b484a24828b240d1a28bf","observation_id":"f7967cf4-9973-498a-a78d-da105dbca8ad","resolution":{"observed_at":"2026-08-01T01:14:56.594329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.681415Z","title":"Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.681415Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:c1c2b6cb9128e14fee267c6b382f0d573747ca2169db030f8b5ce1b4cedede84","observation_id":"8edc57f5-38de-44b8-93b0-e52e67ad987b","resolution":{"observed_at":"2026-08-01T01:14:56.681415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.738073Z","title":"CAMD: Context- aware masked distillation for general self-supervised facial representa- tion pre-training,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.738073Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:214a8db04ff9954cacd2c884c73a11ee816df0b76129af8cf5e18d595c11035f","observation_id":"8b4f5904-f5b6-48ea-9da2-9adc0b234747","resolution":{"observed_at":"2026-08-01T01:14:56.738073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.788920Z","title":"Mobile edge intelligence for large language models: A contemporary survey,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.788920Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:1140bc746290d8d1cc25d8c0ea679ca6041f1e68441e2fcd1f18f9c13732e4ba","observation_id":"940e3e46-b4cf-497f-a2ef-811d832b9190","resolution":{"observed_at":"2026-08-01T01:14:56.788920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.870054Z","title":"HASFL: Heterogeneity- aware Split Federated Learning over Edge Computing Systems,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.870054Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:71e6db68bebea065913022fc18f4d60dfb0dae95929781d07a1e4c07a0083215","observation_id":"b0e1a346-6627-4648-9c0e-715f3c8105e9","resolution":{"observed_at":"2026-08-01T01:14:56.870054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:56.946488Z","title":"Global texture enhancement for fake face detection in the wild,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:56.946488Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:90d630b8daacb10029624485a6b4bbc06e36ec8e5ee6a12f2b45c59f6226a14a","observation_id":"1e451f6a-5964-4f6a-a0b0-2c79a5bfe805","resolution":{"observed_at":"2026-08-01T01:14:56.946488Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:57.106345Z","title":"Image manipulation detection by multi-view multi-scale supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:57.106345Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:4ef44d57ac78176bf30cbd309bc2b2a71c97b065eca4246a2496afbb8f00ea2b","observation_id":"cb12c98a-603f-4b02-b53e-e6ace29b161c","resolution":{"observed_at":"2026-08-01T01:14:57.106345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:57.266553Z","title":"Dual frequency branch frame- work with reconstructed sliding windows attention for AI-generated image detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:57.266553Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:57a0f66ad668be19d3db9a363d7f7a857e9344d6d5d3e8ea5f57e81b13e78bb1","observation_id":"f6d08d17-6dd8-4bab-8bcb-bab78de55543","resolution":{"observed_at":"2026-08-01T01:14:57.266553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:57.514165Z","title":"Frequency-aware deepfake detection: Improving generalizability through frequency space learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:57.514165Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:b5264a4dd5498235ce140adc03e7fd83f0d2e6184af9358f1209e7757723eeda","observation_id":"cfd61d44-24ea-44e5-ac72-37745da4578c","resolution":{"observed_at":"2026-08-01T01:14:57.514165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:57.625806Z","title":"A sanity check for AI-generated image detection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:57.625806Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:0e7d88c5c433ee819f6dbbcfab58e5e28650b180c48e412ba5b2255b963198e8","observation_id":"7627f607-8085-4316-bd18-1da198b39978","resolution":{"observed_at":"2026-08-01T01:14:57.625806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.06676","last_updated":"2026-05-21T11:33:51Z","snapshot_observed_at":"2026-08-13T06:12:06.923893Z","submitted_at":"2026-02-06T13:03:26Z","title":"Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.06676","snapshot_observed_at":"2026-08-01T01:14:57.733225Z","title":"Can we build a monolithic model for fake image detection? SICA: Semantic-induced constrained adaptation for unified- yet-discriminative artifact feature space reconstruction,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:57.733225Z"},"links":{"cited_paper":"/paper/2602.06676","citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:f852f9161787f0cbc2e2d727ace6de3602d8510310d720bbff4c94f5c71a8307","observation_id":"fdee8d83-6365-4a19-a0b7-6ab9522a2b2e","resolution":{"observed_at":"2026-08-01T01:14:57.733225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:57.784977Z","title":"IMDL-BenCo: A comprehensive benchmark and codebase for image manipulation detection & localization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:57.784977Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:912bfa18dfb701159b280004b09f29bf7b6a0d2eb4b24d19c2da2f820aeda28f","observation_id":"1a2ba999-3788-420e-b46a-d92e911d9513","resolution":{"observed_at":"2026-08-01T01:14:57.784977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:57.861820Z","title":"ForensicHub: A unified benchmark & codebase for all-domain fake image detection and localization,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:57.861820Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:f427b66f5e7470dee33819dbddf6b0ef6cfa264c1daf394b881ae89173a5f9f1","observation_id":"4f0d7043-a722-45fb-b6b7-0a91432fb798","resolution":{"observed_at":"2026-08-01T01:14:57.861820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:57.965474Z","title":"Is artificial intelligence generated image detection a solved problem?","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:57.965474Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:de4a11e8f31d6eab63ec467107f14df1605b707aa6e7944260e8a89ed2416e3f","observation_id":"1f29a543-913e-40b0-9934-fe222c1470ad","resolution":{"observed_at":"2026-08-01T01:14:57.965474Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.023163Z","title":"Genimage: A million-scale benchmark for detecting AI- generated image,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.023163Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:74935b113c2929fe370942e647e934dbc726eb8723afbc23739066c3bdcb36ae","observation_id":"7341d947-bff0-4e9e-9f18-db82e2b9f4ea","resolution":{"observed_at":"2026-08-01T01:14:58.023163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.064921Z","title":"Revisiting image manipulation localization under realistic manipulation scenarios,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.064921Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:bc614ccbb39a286a47609dc1c922d38d22576a4e806808d76845df9c9e06f02f","observation_id":"3b845410-ad3f-4dfc-81a3-2eff5ab618f1","resolution":{"observed_at":"2026-08-01T01:14:58.064921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.137456Z","title":"AEROBLADE: Training-free detection of latent diffusion images using autoencoder reconstruction error,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.137456Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:f53f4c30f3f7adc14edd07b61f9b55e5367e7e7ab93bfc361eb98d22fd2cd87d","observation_id":"dfc2e0b4-ea3b-47c6-bec5-f6876e7fa2c4","resolution":{"observed_at":"2026-08-01T01:14:58.137456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.220471Z","title":"DRCT: Diffusion reconstruction contrastive training towards universal detection of diffusion generated images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.220471Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:29f6ed10b7a2f222ac1f7304a22b5726960d4b2092d868a9bf5a949efe03fc33","observation_id":"af0c66a5-d6cd-4a04-98a9-3e4aeb32891e","resolution":{"observed_at":"2026-08-01T01:14:58.220471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-12T17:13:46.394331Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-01T01:14:58.292084Z","title":"Explaining and harnessing adversarial examples,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.292084Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:b55045a270561dcb142604d62bd803e67d617e527f1f406558a6fe7f0ffa1d28","observation_id":"e663a541-a34a-4d66-be57-03c8575ea3c5","resolution":{"observed_at":"2026-08-01T01:14:58.292084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.373605Z","title":"Towards deep learning models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.373605Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:6c71c19a327aa0b661d0832398446c09a895faf7f35b439e57e3b27ca8a7cb19","observation_id":"e298c498-9e13-49a4-aeb0-ff275c2dc357","resolution":{"observed_at":"2026-08-01T01:14:58.373605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.448871Z","title":"Towards evaluating the robustness of neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.448871Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:2c7e6e006ab790b56cd9d44598c35c63573d00552f2e608a8b0f245b9d2cfe52","observation_id":"16affd31-bbb6-4470-8e2f-2c8e5aec9b24","resolution":{"observed_at":"2026-08-01T01:14:58.448871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.530470Z","title":"Practical black-box attacks against machine learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.530470Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:aa7f34fbb79d9af7846dd00d89e8780a23ef412bd4f589cfac6b9e4fd59cc055","observation_id":"37638f85-a2f7-4a80-b1f0-aa778b7da28f","resolution":{"observed_at":"2026-08-01T01:14:58.530470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.586193Z","title":"Boosting adversarial attacks with momentum,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.586193Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:890e2a8a6473c3c5ae9af9f05aed4b99150783ca6352773b4a9cdbe2579fb88d","observation_id":"6fcb1b64-9fc4-433b-9987-886374c66556","resolution":{"observed_at":"2026-08-01T01:14:58.586193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.653436Z","title":"Simple black-box adversarial attacks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.653436Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:e36a95b2ff4342359c9bbd37d104bc70a6e8b2bf6f0a93dfe0808bfeeea06d12","observation_id":"1d270d0e-c7dc-49e1-8316-bb82df3b08a8","resolution":{"observed_at":"2026-08-01T01:14:58.653436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.755797Z","title":"Square at- tack: A query-efficient black-box adversarial attack via random search,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.755797Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:bf35201a160ffb3119247bb5a0485ab1307ff3bd1fc8e47edc77e6b39deb767d","observation_id":"2ab1a43e-a8c0-471e-ab76-c69cb2afdbb6","resolution":{"observed_at":"2026-08-01T01:14:58.755797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.837882Z","title":"BRUSLEATTACK: A query-efficient score-based black-box sparse adversarial attack,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.837882Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:3a15a50edb0c7321b0b3a1d8e2ef4304d43c325926bd086b59c059552c6748d6","observation_id":"27068082-94fb-413f-a8b7-97a676b6d274","resolution":{"observed_at":"2026-08-01T01:14:58.837882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.917194Z","title":"DP-RAE: A dual-phase merging reversible adversarial example for image privacy protection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.917194Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:9fc48e39f2ad50c7f03995c80749ce5c1891171a28bd3edbaaf92381c51ffb0c","observation_id":"d3343a69-ae63-46b9-a966-9ac15918b0c6","resolution":{"observed_at":"2026-08-01T01:14:58.917194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:58.995988Z","title":"Guided evolutionary strategies: Augmenting random search with surrogate gradients,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:58.995988Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:46e2a9a4e82c73cdefe9c3b56ecfa169e08852d13af4b30419508073ffb7a513","observation_id":"e28c1453-77a6-4fd4-9c24-6d94c1178060","resolution":{"observed_at":"2026-08-01T01:14:58.995988Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.077293Z","title":"Improving black- box adversarial attacks with a transfer-based prior,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.077293Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:5e92ed118c5124fab87bc1ae9b2394329d23b74df2e8662613d1304768fbc89f","observation_id":"846632fb-a8f1-49fb-ad53-b8d7ca2c5f05","resolution":{"observed_at":"2026-08-01T01:14:59.077293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.145301Z","title":"Adversarial Deepfakes: Evaluating vulnerability of Deepfake detectors to adversarial examples,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.145301Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:d145662566b751e0824ad9f697d68052ccdfacf21481a1cb6650b8b21d3ddf97","observation_id":"e5389de8-ef75-4f27-a2bb-b085aa08b3f7","resolution":{"observed_at":"2026-08-01T01:14:59.145301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.194927Z","title":"Evading Deep- fake detectors via adversarial statistical consistency,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.194927Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:19ecd9d18fac6a69edb1cb61d10b1b13a42502bcfecbcdfbf78f41af8d181fba","observation_id":"4e5185ba-5501-44b6-a314-4ec679beaa80","resolution":{"observed_at":"2026-08-01T01:14:59.194927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.236911Z","title":"MaskGAN: Towards diverse and interactive facial image manipulation,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.236911Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:a72502d667bc32265c5d20ade1bd752a726870bb6d11d025e1019faef605b4ca","observation_id":"632520a5-a857-4e74-8bc6-5a63896131b2","resolution":{"observed_at":"2026-08-01T01:14:59.236911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.280156Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.280156Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:8953c9ea33827279f534c6f36ba284345625bca95235a60a4815e71870add980","observation_id":"96894722-f037-4cda-976c-dfd645f5bf8e","resolution":{"observed_at":"2026-08-01T01:14:59.280156Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.283406Z","title":"EfficientNet: Rethinking model scaling for con- volutional neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.283406Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:cbcf643cd26c33deb70a5f6adb47be27078dd68abcf6006aafb33e25c36eff1b","observation_id":"419af507-011a-48fc-871d-7b06be3aa731","resolution":{"observed_at":"2026-08-01T01:14:59.283406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.293188Z","title":"Training data-efficient image transformers & distillation through attention,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.293188Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:c0cbd6b465baf1716c5e6e0b2b2f033e660665e0a65726a4a1b67ef4d8a5f00d","observation_id":"3d872d4a-38ca-4d53-927b-fad8b5f2e69e","resolution":{"observed_at":"2026-08-01T01:14:59.293188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.436491Z","title":"Swin Transformer: Hierarchical vision transformer using shifted win- dows,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.436491Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:9b4d02661e1808d84111ee7f657ec29232fcafa7d0dee5fb7abb3a4265885823","observation_id":"1c2221f1-38d3-48f1-998e-99de748e65d0","resolution":{"observed_at":"2026-08-01T01:14:59.436491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.592071Z","title":"Orthogonal subspace decomposition for generalizable AI-generated image detection,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.592071Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:ffbce2b9df5086f1e0fb8280ee25a16629e67222a6d7c8c1f4f157a66dc37150","observation_id":"d5796985-65e1-40c0-9274-6936951563e5","resolution":{"observed_at":"2026-08-01T01:14:59.592071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.819915Z","title":"PGC: Peak-guided calibration for generalizable AI-generated image detection,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.819915Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:d3a06bc2694157c04e2e25425b3a4321d699dc0a9417eb10aae994e0aa4e2d27","observation_id":"490c3afb-b17f-414c-b066-2983915a4996","resolution":{"observed_at":"2026-08-01T01:14:59.819915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:14:59.661794Z","title":"70 268–70 288","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors","version":1},"reference_index":267,"source":"pdf_text","source_observed_at":"2026-08-01T01:14:59.661794Z"},"links":{"citing_paper":"/paper/2607.25894"},"observation_digest":"sha256:46dabbad2d42f8a717fde3d6dccb7af2b81f7236e17560e0bf4f9175215beb05","observation_id":"e38d0f9a-bc2c-4ec9-a934-41e3b9bc37aa","resolution":{"observed_at":"2026-08-01T01:14:59.661794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.25894","last_updated":"2026-07-28T15:51:39Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T09:01:06.994814Z","submitted_at":"2026-07-28T15:51:39Z","title":"TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors"},"reference_resolution":{"displayed":66,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":66,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":66},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2607.25894."}