{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPQY7C5FJRCKBHVFQOB4UDRZAP","short_pith_number":"pith:KPQY7C5F","schema_version":"1.0","canonical_sha256":"53e18f8ba54c44a09ea58383ca0e3903dc417e78a2eefc0334add8ef3eba5a26","source":{"kind":"arxiv","id":"2403.06700","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Chao Li, Fanyang Meng, Genhong Wang, Wen Tan, Yongsheng Liang, Youneng Bao, Zhi Cao","submitted_at":"2024-03-11T13:16:44Z","abstract_excerpt":"Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a common method to enhance model robustness. However, the improvement effect of adversarial training on model robustness is limited. In this paper, we propose a prior knowledge-guided adversarial training framework for image compression models. Specifically, first, we propose a gradient regularization constraint for training robust teacher models. Subsequently, we"},"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":"2403.06700","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-03-11T13:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"29627267468c414b1d283f04b9b75d195d9889fd1fa53572bd48c89b70ac3768","abstract_canon_sha256":"a39e20b00fc2adfb9cb516c2cf2a70472957e1c6bfa3b64c40c440d4288372b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:01.515141Z","signature_b64":"+g8rF/orLOWidEiX8KPsSisdViPL76rqbeR5YoU2yedmbouMo6H3nUWX0DHSD8HfIg/BTT0dERuoy0TWGXWsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e18f8ba54c44a09ea58383ca0e3903dc417e78a2eefc0334add8ef3eba5a26","last_reissued_at":"2026-07-05T07:57:01.514703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:01.514703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Chao Li, Fanyang Meng, Genhong Wang, Wen Tan, Yongsheng Liang, Youneng Bao, Zhi Cao","submitted_at":"2024-03-11T13:16:44Z","abstract_excerpt":"Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a common method to enhance model robustness. However, the improvement effect of adversarial training on model robustness is limited. In this paper, we propose a prior knowledge-guided adversarial training framework for image compression models. Specifically, first, we propose a gradient regularization constraint for training robust teacher models. Subsequently, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06700","kind":"arxiv","version":2},"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/2403.06700/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":"2403.06700","created_at":"2026-07-05T07:57:01.514761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06700v2","created_at":"2026-07-05T07:57:01.514761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06700","created_at":"2026-07-05T07:57:01.514761+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPQY7C5FJRCK","created_at":"2026-07-05T07:57:01.514761+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPQY7C5FJRCKBHVF","created_at":"2026-07-05T07:57:01.514761+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPQY7C5F","created_at":"2026-07-05T07:57:01.514761+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/KPQY7C5FJRCKBHVFQOB4UDRZAP","json":"https://pith.science/pith/KPQY7C5FJRCKBHVFQOB4UDRZAP.json","graph_json":"https://pith.science/api/pith-number/KPQY7C5FJRCKBHVFQOB4UDRZAP/graph.json","events_json":"https://pith.science/api/pith-number/KPQY7C5FJRCKBHVFQOB4UDRZAP/events.json","paper":"https://pith.science/paper/KPQY7C5F"},"agent_actions":{"view_html":"https://pith.science/pith/KPQY7C5FJRCKBHVFQOB4UDRZAP","download_json":"https://pith.science/pith/KPQY7C5FJRCKBHVFQOB4UDRZAP.json","view_paper":"https://pith.science/paper/KPQY7C5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06700&json=true","fetch_graph":"https://pith.science/api/pith-number/KPQY7C5FJRCKBHVFQOB4UDRZAP/graph.json","fetch_events":"https://pith.science/api/pith-number/KPQY7C5FJRCKBHVFQOB4UDRZAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPQY7C5FJRCKBHVFQOB4UDRZAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPQY7C5FJRCKBHVFQOB4UDRZAP/action/storage_attestation","attest_author":"https://pith.science/pith/KPQY7C5FJRCKBHVFQOB4UDRZAP/action/author_attestation","sign_citation":"https://pith.science/pith/KPQY7C5FJRCKBHVFQOB4UDRZAP/action/citation_signature","submit_replication":"https://pith.science/pith/KPQY7C5FJRCKBHVFQOB4UDRZAP/action/replication_record"}},"created_at":"2026-07-05T07:57:01.514761+00:00","updated_at":"2026-07-05T07:57:01.514761+00:00"}