{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6W4H5YRJ23JR7YPAJC5CALMG7Z","short_pith_number":"pith:6W4H5YRJ","schema_version":"1.0","canonical_sha256":"f5b87ee229d6d31fe1e048ba202d86fe5fcc4670a9e99c75ea966f7718c4b68c","source":{"kind":"arxiv","id":"2412.03261","version":2},"attestation_state":"computed","paper":{"title":"Is JPEG AI going to change image forensics?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Alessandro Gnutti, Ayman Alkhateeb, Edoardo Daniele Cannas, Nata\\v{s}a Popovi\\'c, Paolo Bestagini, Sara Mandelli, Stefano Tubaro","submitted_at":"2024-12-04T12:07:20Z","abstract_excerpt":"In this paper, we investigate the counter-forensic effects of the new JPEG AI standard based on neural image compression, focusing on two critical areas: deepfake image detection and image splicing localization. Neural image compression leverages advanced neural network algorithms to achieve higher compression rates while maintaining image quality. However, it introduces artifacts that closely resemble those generated by image synthesis techniques and image splicing pipelines, complicating the work of researchers when discriminating pristine from manipulated content. We comprehensively analyze"},"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":"2412.03261","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-12-04T12:07:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b889bdeb95823f9a9f58a438f23b0bad9baf1ca5f9b2f76727525613f23a0314","abstract_canon_sha256":"4a6491e3961193f5d0c731cbf3944eb88995a769a5898152893b8844bbaba5f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:40.783356Z","signature_b64":"0itKsUXJI0ZtbGy05eKm6duYPFvTgRH2ecB1KZF+ZCijoQT6cxu49nP+etXxMFO7KAo1Y3YFBxqux4Rq7adQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b87ee229d6d31fe1e048ba202d86fe5fcc4670a9e99c75ea966f7718c4b68c","last_reissued_at":"2026-07-05T10:33:40.782372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:40.782372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is JPEG AI going to change image forensics?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Alessandro Gnutti, Ayman Alkhateeb, Edoardo Daniele Cannas, Nata\\v{s}a Popovi\\'c, Paolo Bestagini, Sara Mandelli, Stefano Tubaro","submitted_at":"2024-12-04T12:07:20Z","abstract_excerpt":"In this paper, we investigate the counter-forensic effects of the new JPEG AI standard based on neural image compression, focusing on two critical areas: deepfake image detection and image splicing localization. Neural image compression leverages advanced neural network algorithms to achieve higher compression rates while maintaining image quality. However, it introduces artifacts that closely resemble those generated by image synthesis techniques and image splicing pipelines, complicating the work of researchers when discriminating pristine from manipulated content. We comprehensively analyze"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03261","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/2412.03261/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":"2412.03261","created_at":"2026-07-05T10:33:40.782523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03261v2","created_at":"2026-07-05T10:33:40.782523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03261","created_at":"2026-07-05T10:33:40.782523+00:00"},{"alias_kind":"pith_short_12","alias_value":"6W4H5YRJ23JR","created_at":"2026-07-05T10:33:40.782523+00:00"},{"alias_kind":"pith_short_16","alias_value":"6W4H5YRJ23JR7YPA","created_at":"2026-07-05T10:33:40.782523+00:00"},{"alias_kind":"pith_short_8","alias_value":"6W4H5YRJ","created_at":"2026-07-05T10:33:40.782523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02224","citing_title":"Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z","json":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z.json","graph_json":"https://pith.science/api/pith-number/6W4H5YRJ23JR7YPAJC5CALMG7Z/graph.json","events_json":"https://pith.science/api/pith-number/6W4H5YRJ23JR7YPAJC5CALMG7Z/events.json","paper":"https://pith.science/paper/6W4H5YRJ"},"agent_actions":{"view_html":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z","download_json":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z.json","view_paper":"https://pith.science/paper/6W4H5YRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03261&json=true","fetch_graph":"https://pith.science/api/pith-number/6W4H5YRJ23JR7YPAJC5CALMG7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/6W4H5YRJ23JR7YPAJC5CALMG7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z/action/storage_attestation","attest_author":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z/action/author_attestation","sign_citation":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z/action/citation_signature","submit_replication":"https://pith.science/pith/6W4H5YRJ23JR7YPAJC5CALMG7Z/action/replication_record"}},"created_at":"2026-07-05T10:33:40.782523+00:00","updated_at":"2026-07-05T10:33:40.782523+00:00"}