{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KCXZCFCQPICBEP6VSTNLWI3PT7","short_pith_number":"pith:KCXZCFCQ","schema_version":"1.0","canonical_sha256":"50af9114507a04123fd594dabb236f9fc442af3ae948de0258a288eb74b1afcf","source":{"kind":"arxiv","id":"2410.02761","version":4},"attestation_state":"computed","paper":{"title":"FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Qing Huang, Runyi Li, Xuanyu Zhang, Zecheng Tang, Zhipei Xu","submitted_at":"2024-10-03T17:59:34Z","abstract_excerpt":"The rapid development of generative AI is a double-edged sword, which not only facilitates content creation but also makes image manipulation easier and more difficult to detect. Although current image forgery detection and localization (IFDL) methods are generally effective, they tend to face two challenges: \\textbf{1)} black-box nature with unknown detection principle, \\textbf{2)} limited generalization across diverse tampering methods (e.g., Photoshop, DeepFake, AIGC-Editing). To address these issues, we propose the explainable IFDL task and design FakeShield, a multi-modal framework capabl"},"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":"2410.02761","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:59:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e661c3f431f128defecaa57b26b6fb777204cb7b9660215f1df5fd5068686c3","abstract_canon_sha256":"139bb01bdc6a40757627e10d707c4b5b1ed225da63255ba3cb68ed6550c9d09b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:55.567612Z","signature_b64":"wHEay+GPZ/5MpfmfmC7l3lUXQrRJiRXcv0FgXIV1wzCxjUPNPTT4WPxUWoDOFMXZMp4WCpU1lgPlgVIoz0XPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50af9114507a04123fd594dabb236f9fc442af3ae948de0258a288eb74b1afcf","last_reissued_at":"2026-07-05T10:47:55.567088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:55.567088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Qing Huang, Runyi Li, Xuanyu Zhang, Zecheng Tang, Zhipei Xu","submitted_at":"2024-10-03T17:59:34Z","abstract_excerpt":"The rapid development of generative AI is a double-edged sword, which not only facilitates content creation but also makes image manipulation easier and more difficult to detect. Although current image forgery detection and localization (IFDL) methods are generally effective, they tend to face two challenges: \\textbf{1)} black-box nature with unknown detection principle, \\textbf{2)} limited generalization across diverse tampering methods (e.g., Photoshop, DeepFake, AIGC-Editing). To address these issues, we propose the explainable IFDL task and design FakeShield, a multi-modal framework capabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02761","kind":"arxiv","version":4},"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/2410.02761/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":"2410.02761","created_at":"2026-07-05T10:47:55.567153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02761v4","created_at":"2026-07-05T10:47:55.567153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02761","created_at":"2026-07-05T10:47:55.567153+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCXZCFCQPICB","created_at":"2026-07-05T10:47:55.567153+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCXZCFCQPICBEP6V","created_at":"2026-07-05T10:47:55.567153+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCXZCFCQ","created_at":"2026-07-05T10:47:55.567153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25375","citing_title":"Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25375","citing_title":"Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07171","citing_title":"When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26421","citing_title":"HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00101","citing_title":"CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30062","citing_title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21210","citing_title":"Toward Generalizable Forgery Detection and Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15693","citing_title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04225","citing_title":"Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7","json":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7.json","graph_json":"https://pith.science/api/pith-number/KCXZCFCQPICBEP6VSTNLWI3PT7/graph.json","events_json":"https://pith.science/api/pith-number/KCXZCFCQPICBEP6VSTNLWI3PT7/events.json","paper":"https://pith.science/paper/KCXZCFCQ"},"agent_actions":{"view_html":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7","download_json":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7.json","view_paper":"https://pith.science/paper/KCXZCFCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02761&json=true","fetch_graph":"https://pith.science/api/pith-number/KCXZCFCQPICBEP6VSTNLWI3PT7/graph.json","fetch_events":"https://pith.science/api/pith-number/KCXZCFCQPICBEP6VSTNLWI3PT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7/action/storage_attestation","attest_author":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7/action/author_attestation","sign_citation":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7/action/citation_signature","submit_replication":"https://pith.science/pith/KCXZCFCQPICBEP6VSTNLWI3PT7/action/replication_record"}},"created_at":"2026-07-05T10:47:55.567153+00:00","updated_at":"2026-07-05T10:47:55.567153+00:00"}