{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NSE2343XOD32R5JOKDPGTOP76H","short_pith_number":"pith:NSE2343X","schema_version":"1.0","canonical_sha256":"6c89adf37770f7a8f52e50de69b9fff1dd656bfcc0183ecb6f60f80475f9c021","source":{"kind":"arxiv","id":"2112.03553","version":1},"attestation_state":"computed","paper":{"title":"ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binh M. Le, Simon S. Woo","submitted_at":"2021-12-07T07:58:28Z","abstract_excerpt":"Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed deepfake images. Because of the limited information in low-quality images, detecting low-quality deepfake remains an important challenge. In this work, we apply frequency domain learning and optimal transport theory in knowledge distillation (KD) to specifically improve the detection of low-quality compressed deepfake images. We explore transfer learning capabil"},"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":"2112.03553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-07T07:58:28Z","cross_cats_sorted":[],"title_canon_sha256":"2efe64797a8bbad0a2b79b4ead2c6eccc7c96fa9f3be704244ab80a5030da25a","abstract_canon_sha256":"d18ad9d1209ce40352b9a42266ce1aa9c20f2cc55dc962192e0973ee64e2e514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:46.729044Z","signature_b64":"F4k5X3tMQN9vx9PUOnI8M7/bAdWYWcf/8cld8IN8k1APAlOg4FmGlrnNYkC9MOaOWzsXxL2alQAJg+hexGPkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c89adf37770f7a8f52e50de69b9fff1dd656bfcc0183ecb6f60f80475f9c021","last_reissued_at":"2026-07-05T03:38:46.728589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:46.728589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binh M. Le, Simon S. Woo","submitted_at":"2021-12-07T07:58:28Z","abstract_excerpt":"Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed deepfake images. Because of the limited information in low-quality images, detecting low-quality deepfake remains an important challenge. In this work, we apply frequency domain learning and optimal transport theory in knowledge distillation (KD) to specifically improve the detection of low-quality compressed deepfake images. We explore transfer learning capabil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03553","kind":"arxiv","version":1},"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/2112.03553/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":"2112.03553","created_at":"2026-07-05T03:38:46.728641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03553v1","created_at":"2026-07-05T03:38:46.728641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03553","created_at":"2026-07-05T03:38:46.728641+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSE2343XOD32","created_at":"2026-07-05T03:38:46.728641+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSE2343XOD32R5JO","created_at":"2026-07-05T03:38:46.728641+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSE2343X","created_at":"2026-07-05T03:38:46.728641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22469","citing_title":"Visual Language Models as Zero-Shot Deepfake Detectors","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H","json":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H.json","graph_json":"https://pith.science/api/pith-number/NSE2343XOD32R5JOKDPGTOP76H/graph.json","events_json":"https://pith.science/api/pith-number/NSE2343XOD32R5JOKDPGTOP76H/events.json","paper":"https://pith.science/paper/NSE2343X"},"agent_actions":{"view_html":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H","download_json":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H.json","view_paper":"https://pith.science/paper/NSE2343X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03553&json=true","fetch_graph":"https://pith.science/api/pith-number/NSE2343XOD32R5JOKDPGTOP76H/graph.json","fetch_events":"https://pith.science/api/pith-number/NSE2343XOD32R5JOKDPGTOP76H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H/action/storage_attestation","attest_author":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H/action/author_attestation","sign_citation":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H/action/citation_signature","submit_replication":"https://pith.science/pith/NSE2343XOD32R5JOKDPGTOP76H/action/replication_record"}},"created_at":"2026-07-05T03:38:46.728641+00:00","updated_at":"2026-07-05T03:38:46.728641+00:00"}