{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7QLEPVPGCJWI4TZYULVDSWKUNS","short_pith_number":"pith:7QLEPVPG","schema_version":"1.0","canonical_sha256":"fc1647d5e6126c8e4f38a2ea3959546ca166c259d1f0929edc1d898d3efd00af","source":{"kind":"arxiv","id":"2411.11795","version":1},"attestation_state":"computed","paper":{"title":"Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Aleksandr Gushchin, Anastasia Antsiferova, Anna Chistyakova, Dmitriy Vatolin, Egor Kovalev, Georgii Bychkov, Khaled Abud, Sergey Lavrushkin","submitted_at":"2024-11-18T18:08:52Z","abstract_excerpt":"Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI - the first standard for end-to-end neural image compression (NIC) methods - the question of its robustness has become critically significant. JPEG AI is among the first international, real-world applications of neural-network-based models to be embedded in consumer devices. However, research on NIC robustness has been limited to open-source codecs and a narrow range of attacks. This paper pro"},"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":"2411.11795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-11-18T18:08:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"db5e07eebcd91d7ff4552b860849eeab8b2124815e89410cdbd766cf874e24d9","abstract_canon_sha256":"6d90c8925037b2e4168b901b8df16f82f4b36d2060713b39e354598eb51597e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:01.783511Z","signature_b64":"vEgy07HYvu2e9CU2Ity5kI7OdKFPMVg2rHf/epRRjB+LrvvsBqG2ixLDrkdjc6/sN2CqAraOZq9ctlOt/EVoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc1647d5e6126c8e4f38a2ea3959546ca166c259d1f0929edc1d898d3efd00af","last_reissued_at":"2026-07-05T09:37:01.781720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:01.781720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Aleksandr Gushchin, Anastasia Antsiferova, Anna Chistyakova, Dmitriy Vatolin, Egor Kovalev, Georgii Bychkov, Khaled Abud, Sergey Lavrushkin","submitted_at":"2024-11-18T18:08:52Z","abstract_excerpt":"Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI - the first standard for end-to-end neural image compression (NIC) methods - the question of its robustness has become critically significant. JPEG AI is among the first international, real-world applications of neural-network-based models to be embedded in consumer devices. However, research on NIC robustness has been limited to open-source codecs and a narrow range of attacks. This paper pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11795","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/2411.11795/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":"2411.11795","created_at":"2026-07-05T09:37:01.782891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11795v1","created_at":"2026-07-05T09:37:01.782891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11795","created_at":"2026-07-05T09:37:01.782891+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QLEPVPGCJWI","created_at":"2026-07-05T09:37:01.782891+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QLEPVPGCJWI4TZY","created_at":"2026-07-05T09:37:01.782891+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QLEPVPG","created_at":"2026-07-05T09:37:01.782891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS","json":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS.json","graph_json":"https://pith.science/api/pith-number/7QLEPVPGCJWI4TZYULVDSWKUNS/graph.json","events_json":"https://pith.science/api/pith-number/7QLEPVPGCJWI4TZYULVDSWKUNS/events.json","paper":"https://pith.science/paper/7QLEPVPG"},"agent_actions":{"view_html":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS","download_json":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS.json","view_paper":"https://pith.science/paper/7QLEPVPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11795&json=true","fetch_graph":"https://pith.science/api/pith-number/7QLEPVPGCJWI4TZYULVDSWKUNS/graph.json","fetch_events":"https://pith.science/api/pith-number/7QLEPVPGCJWI4TZYULVDSWKUNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS/action/storage_attestation","attest_author":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS/action/author_attestation","sign_citation":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS/action/citation_signature","submit_replication":"https://pith.science/pith/7QLEPVPGCJWI4TZYULVDSWKUNS/action/replication_record"}},"created_at":"2026-07-05T09:37:01.782891+00:00","updated_at":"2026-07-05T09:37:01.782891+00:00"}