{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AZXJITJBIYI22W3X4ASUYMID27","short_pith_number":"pith:AZXJITJB","schema_version":"1.0","canonical_sha256":"066e944d214611ad5b77e0254c3103d7cb02bf6ec5a02e47077336b6e32f5232","source":{"kind":"arxiv","id":"2210.14571","version":4},"attestation_state":"computed","paper":{"title":"Towards the Detection of Diffusion Model Deepfakes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Asja Fischer, Jonas Ricker, Simon Damm, Thorsten Holz","submitted_at":"2022-10-26T09:01:19Z","abstract_excerpt":"In the course of the past few years, diffusion models (DMs) have reached an unprecedented level of visual quality. However, relatively little attention has been paid to the detection of DM-generated images, which is critical to prevent adverse impacts on our society. In contrast, generative adversarial networks (GANs), have been extensively studied from a forensic perspective. In this work, we therefore take the natural next step to evaluate whether previous methods can be used to detect images generated by DMs. Our experiments yield two key findings: (1) state-of-the-art GAN detectors are una"},"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":"2210.14571","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-26T09:01:19Z","cross_cats_sorted":[],"title_canon_sha256":"f0bf3a1cfba4b2ccfd5bc1d3439cd48a745db33fc1023649d1d8434a6e03a517","abstract_canon_sha256":"e1f6341e26c3b188ce7ccfcbca54a0434c4c8ab12d9b93c01d47992d56aceb8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:58.815870Z","signature_b64":"LZg9aqvVMrLJpusx0cKEcfAA8BHZBGJIRJcpjnLASoCB1kvqZxNYwSyAO7/guLjeYkVUzyQnm0dcdwb6+YQiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"066e944d214611ad5b77e0254c3103d7cb02bf6ec5a02e47077336b6e32f5232","last_reissued_at":"2026-07-05T07:35:58.815352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:58.815352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards the Detection of Diffusion Model Deepfakes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Asja Fischer, Jonas Ricker, Simon Damm, Thorsten Holz","submitted_at":"2022-10-26T09:01:19Z","abstract_excerpt":"In the course of the past few years, diffusion models (DMs) have reached an unprecedented level of visual quality. However, relatively little attention has been paid to the detection of DM-generated images, which is critical to prevent adverse impacts on our society. In contrast, generative adversarial networks (GANs), have been extensively studied from a forensic perspective. In this work, we therefore take the natural next step to evaluate whether previous methods can be used to detect images generated by DMs. Our experiments yield two key findings: (1) state-of-the-art GAN detectors are una"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14571","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/2210.14571/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":"2210.14571","created_at":"2026-07-05T07:35:58.815417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14571v4","created_at":"2026-07-05T07:35:58.815417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14571","created_at":"2026-07-05T07:35:58.815417+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZXJITJBIYI2","created_at":"2026-07-05T07:35:58.815417+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZXJITJBIYI22W3X","created_at":"2026-07-05T07:35:58.815417+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZXJITJB","created_at":"2026-07-05T07:35:58.815417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28510","citing_title":"Generative AI Literacy Training Improves Intelligence Analysts' Discrimination of Real and AI-Generated Images","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14799","citing_title":"Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21864","citing_title":"Deepfakes: we need to re-think the concept of \"real\" images","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10522","citing_title":"SEED: A Large-Scale Benchmark for Provenance Tracing in Sequential Deepfake Facial Edits","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27","json":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27.json","graph_json":"https://pith.science/api/pith-number/AZXJITJBIYI22W3X4ASUYMID27/graph.json","events_json":"https://pith.science/api/pith-number/AZXJITJBIYI22W3X4ASUYMID27/events.json","paper":"https://pith.science/paper/AZXJITJB"},"agent_actions":{"view_html":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27","download_json":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27.json","view_paper":"https://pith.science/paper/AZXJITJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14571&json=true","fetch_graph":"https://pith.science/api/pith-number/AZXJITJBIYI22W3X4ASUYMID27/graph.json","fetch_events":"https://pith.science/api/pith-number/AZXJITJBIYI22W3X4ASUYMID27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27/action/storage_attestation","attest_author":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27/action/author_attestation","sign_citation":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27/action/citation_signature","submit_replication":"https://pith.science/pith/AZXJITJBIYI22W3X4ASUYMID27/action/replication_record"}},"created_at":"2026-07-05T07:35:58.815417+00:00","updated_at":"2026-07-05T07:35:58.815417+00:00"}