{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KYMAKAZYMLZM2CL6L7DAHBBBGP","short_pith_number":"pith:KYMAKAZY","schema_version":"1.0","canonical_sha256":"561805033862f2cd097e5fc603842133d416bdabc639b7e73031605853372e07","source":{"kind":"arxiv","id":"2303.15127","version":1},"attestation_state":"computed","paper":{"title":"Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng-zhong Xu, Juanjuan Zhao, Kejiang Ye, Tianrui Qin, Xitong Gao","submitted_at":"2023-03-27T12:00:54Z","abstract_excerpt":"Unlearnable example attacks are data poisoning techniques that can be used to safeguard public data against unauthorized use for training deep learning models. These methods add stealthy perturbations to the original image, thereby making it difficult for deep learning models to learn from these training data effectively. Current research suggests that adversarial training can, to a certain degree, mitigate the impact of unlearnable example attacks, while common data augmentation methods are not effective against such poisons. Adversarial training, however, demands considerable computational r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.15127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-27T12:00:54Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"004e5f7db178912faa4fad78ae2d0a35803194184e5d165a5ef09ba4d37772d8","abstract_canon_sha256":"7c92947f50c9a926828dfba6808606771cfe749c0d88483a6c5f46bb482c3b2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:55:01.474990Z","signature_b64":"AdG4MfNxdBaZ4tmuo7Bvecuq/ATXhGPzzccUAX0gQdg4A5XyEKxh1+u1uFDo3IKl99ZV0lPAwdpLDAAE+9VxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"561805033862f2cd097e5fc603842133d416bdabc639b7e73031605853372e07","last_reissued_at":"2026-07-05T05:55:01.474504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:55:01.474504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Cheng-zhong Xu, Juanjuan Zhao, Kejiang Ye, Tianrui Qin, Xitong Gao","submitted_at":"2023-03-27T12:00:54Z","abstract_excerpt":"Unlearnable example attacks are data poisoning techniques that can be used to safeguard public data against unauthorized use for training deep learning models. These methods add stealthy perturbations to the original image, thereby making it difficult for deep learning models to learn from these training data effectively. Current research suggests that adversarial training can, to a certain degree, mitigate the impact of unlearnable example attacks, while common data augmentation methods are not effective against such poisons. Adversarial training, however, demands considerable computational r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15127","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.15127/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.15127","created_at":"2026-07-05T05:55:01.474555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.15127v1","created_at":"2026-07-05T05:55:01.474555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15127","created_at":"2026-07-05T05:55:01.474555+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYMAKAZYMLZM","created_at":"2026-07-05T05:55:01.474555+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYMAKAZYMLZM2CL6","created_at":"2026-07-05T05:55:01.474555+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYMAKAZY","created_at":"2026-07-05T05:55:01.474555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06484","citing_title":"Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01718","citing_title":"Dual-branch Robust Unlearnable Examples","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02883","citing_title":"Nonlinear Transformations Against Unlearnable Datasets","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24350","citing_title":"Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01718","citing_title":"Dual-branch Robust Unlearnable Examples","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05224","citing_title":"Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP","json":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP.json","graph_json":"https://pith.science/api/pith-number/KYMAKAZYMLZM2CL6L7DAHBBBGP/graph.json","events_json":"https://pith.science/api/pith-number/KYMAKAZYMLZM2CL6L7DAHBBBGP/events.json","paper":"https://pith.science/paper/KYMAKAZY"},"agent_actions":{"view_html":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP","download_json":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP.json","view_paper":"https://pith.science/paper/KYMAKAZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.15127&json=true","fetch_graph":"https://pith.science/api/pith-number/KYMAKAZYMLZM2CL6L7DAHBBBGP/graph.json","fetch_events":"https://pith.science/api/pith-number/KYMAKAZYMLZM2CL6L7DAHBBBGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP/action/storage_attestation","attest_author":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP/action/author_attestation","sign_citation":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP/action/citation_signature","submit_replication":"https://pith.science/pith/KYMAKAZYMLZM2CL6L7DAHBBBGP/action/replication_record"}},"created_at":"2026-07-05T05:55:01.474555+00:00","updated_at":"2026-07-05T05:55:01.474555+00:00"}