{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BMCSO3GAHJWMYVPKDZJRBWJQBH","short_pith_number":"pith:BMCSO3GA","schema_version":"1.0","canonical_sha256":"0b05276cc03a6ccc55ea1e5310d93009f7ab77a9cac5c8ea01e441ff999b5c53","source":{"kind":"arxiv","id":"2401.10345","version":3},"attestation_state":"computed","paper":{"title":"Attack and Defense Analysis of Learned Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Heming Sun, Minge jing, Tianyu Zhu, Xiankui Xiong, Xuanpeng Zhu, Yibo Fan, Yong Gong","submitted_at":"2024-01-18T19:23:07Z","abstract_excerpt":"Learned image compression (LIC) is becoming more and more popular these years with its high efficiency and outstanding compression quality. Still, the practicality against modified inputs added with specific noise could not be ignored. White-box attacks such as FGSM and PGD use only gradient to compute adversarial images that mislead LIC models to output unexpected results. Our experiments compare the effects of different dimensions such as attack methods, models, qualities, and targets, concluding that in the worst case, there is a 61.55% decrease in PSNR or a 19.15 times increase in bpp unde"},"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":"2401.10345","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-01-18T19:23:07Z","cross_cats_sorted":[],"title_canon_sha256":"4f683a2c57f66090bbdb8b2e4063ccbc3e769db6e2e3304069e89abe4efba3b7","abstract_canon_sha256":"bc21bb6070de79808504e17b5e240d68a3e3b881c653048a1fb3b2a637de98aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:18.355457Z","signature_b64":"8smZ9vWjtArGEvN2Bf8EJP7Dsg0cVBhOYu/XNDTrBxnaPer2OCs/RZr5LuAh21hVjCtllvsBmkXp9ObfUwyoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b05276cc03a6ccc55ea1e5310d93009f7ab77a9cac5c8ea01e441ff999b5c53","last_reissued_at":"2026-07-05T08:01:18.354985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:18.354985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attack and Defense Analysis of Learned Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Heming Sun, Minge jing, Tianyu Zhu, Xiankui Xiong, Xuanpeng Zhu, Yibo Fan, Yong Gong","submitted_at":"2024-01-18T19:23:07Z","abstract_excerpt":"Learned image compression (LIC) is becoming more and more popular these years with its high efficiency and outstanding compression quality. Still, the practicality against modified inputs added with specific noise could not be ignored. White-box attacks such as FGSM and PGD use only gradient to compute adversarial images that mislead LIC models to output unexpected results. Our experiments compare the effects of different dimensions such as attack methods, models, qualities, and targets, concluding that in the worst case, there is a 61.55% decrease in PSNR or a 19.15 times increase in bpp unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10345","kind":"arxiv","version":3},"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/2401.10345/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":"2401.10345","created_at":"2026-07-05T08:01:18.355042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10345v3","created_at":"2026-07-05T08:01:18.355042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10345","created_at":"2026-07-05T08:01:18.355042+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMCSO3GAHJWM","created_at":"2026-07-05T08:01:18.355042+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMCSO3GAHJWMYVPK","created_at":"2026-07-05T08:01:18.355042+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMCSO3GA","created_at":"2026-07-05T08:01:18.355042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11795","citing_title":"Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH","json":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH.json","graph_json":"https://pith.science/api/pith-number/BMCSO3GAHJWMYVPKDZJRBWJQBH/graph.json","events_json":"https://pith.science/api/pith-number/BMCSO3GAHJWMYVPKDZJRBWJQBH/events.json","paper":"https://pith.science/paper/BMCSO3GA"},"agent_actions":{"view_html":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH","download_json":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH.json","view_paper":"https://pith.science/paper/BMCSO3GA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10345&json=true","fetch_graph":"https://pith.science/api/pith-number/BMCSO3GAHJWMYVPKDZJRBWJQBH/graph.json","fetch_events":"https://pith.science/api/pith-number/BMCSO3GAHJWMYVPKDZJRBWJQBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH/action/storage_attestation","attest_author":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH/action/author_attestation","sign_citation":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH/action/citation_signature","submit_replication":"https://pith.science/pith/BMCSO3GAHJWMYVPKDZJRBWJQBH/action/replication_record"}},"created_at":"2026-07-05T08:01:18.355042+00:00","updated_at":"2026-07-05T08:01:18.355042+00:00"}