{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:37LZ4TCZAV3BHHJZB4UAFFFKNY","short_pith_number":"pith:37LZ4TCZ","schema_version":"1.0","canonical_sha256":"dfd79e4c590576139d390f280294aa6e3d3cdf1657bfc50f551f8053b69fb0bc","source":{"kind":"arxiv","id":"1907.06515","version":2},"attestation_state":"computed","paper":{"title":"Detecting and Simulating Artifacts in GAN Fake Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Shih-Fu Chang, Svebor Karaman, Xu Zhang","submitted_at":"2019-07-15T14:22:34Z","abstract_excerpt":"To detect GAN generated images, conventional supervised machine learning algorithms require collection of a number of real and fake images from the targeted GAN model. However, the specific model used by the attacker is often unavailable. To address this, we propose a GAN simulator, AutoGAN, which can simulate the artifacts produced by the common pipeline shared by several popular GAN models. Additionally, we identify a unique artifact caused by the up-sampling component included in the common GAN pipeline. We show theoretically such artifacts are manifested as replications of spectra in the f"},"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":"1907.06515","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-15T14:22:34Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"d3b1479b1578b178921d567404d4ffa52ec1682d23b04f5a017e8fbaf3789b2d","abstract_canon_sha256":"585d8790354e50ce28058acaa0a233a7c703c6508d6dba09fef1f7fa357ede06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:28.721183Z","signature_b64":"v1DjWkHvBoRcdzO2usbEOWiJqg1R+aiv0OPq+7XF1Z+EYZnfxcstpPf1tpCbHitqcVILcViz5/oQt6V3aEGuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfd79e4c590576139d390f280294aa6e3d3cdf1657bfc50f551f8053b69fb0bc","last_reissued_at":"2026-07-05T00:12:28.720659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:28.720659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting and Simulating Artifacts in GAN Fake Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Shih-Fu Chang, Svebor Karaman, Xu Zhang","submitted_at":"2019-07-15T14:22:34Z","abstract_excerpt":"To detect GAN generated images, conventional supervised machine learning algorithms require collection of a number of real and fake images from the targeted GAN model. However, the specific model used by the attacker is often unavailable. To address this, we propose a GAN simulator, AutoGAN, which can simulate the artifacts produced by the common pipeline shared by several popular GAN models. Additionally, we identify a unique artifact caused by the up-sampling component included in the common GAN pipeline. We show theoretically such artifacts are manifested as replications of spectra in the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.06515","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/1907.06515/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":"1907.06515","created_at":"2026-07-05T00:12:28.720714+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.06515v2","created_at":"2026-07-05T00:12:28.720714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.06515","created_at":"2026-07-05T00:12:28.720714+00:00"},{"alias_kind":"pith_short_12","alias_value":"37LZ4TCZAV3B","created_at":"2026-07-05T00:12:28.720714+00:00"},{"alias_kind":"pith_short_16","alias_value":"37LZ4TCZAV3BHHJZ","created_at":"2026-07-05T00:12:28.720714+00:00"},{"alias_kind":"pith_short_8","alias_value":"37LZ4TCZ","created_at":"2026-07-05T00:12:28.720714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":240,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12307","citing_title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY","json":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY.json","graph_json":"https://pith.science/api/pith-number/37LZ4TCZAV3BHHJZB4UAFFFKNY/graph.json","events_json":"https://pith.science/api/pith-number/37LZ4TCZAV3BHHJZB4UAFFFKNY/events.json","paper":"https://pith.science/paper/37LZ4TCZ"},"agent_actions":{"view_html":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY","download_json":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY.json","view_paper":"https://pith.science/paper/37LZ4TCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.06515&json=true","fetch_graph":"https://pith.science/api/pith-number/37LZ4TCZAV3BHHJZB4UAFFFKNY/graph.json","fetch_events":"https://pith.science/api/pith-number/37LZ4TCZAV3BHHJZB4UAFFFKNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY/action/storage_attestation","attest_author":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY/action/author_attestation","sign_citation":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY/action/citation_signature","submit_replication":"https://pith.science/pith/37LZ4TCZAV3BHHJZB4UAFFFKNY/action/replication_record"}},"created_at":"2026-07-05T00:12:28.720714+00:00","updated_at":"2026-07-05T00:12:28.720714+00:00"}