{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JGUYO724SHP7NBOYRKMBXAMKCE","short_pith_number":"pith:JGUYO724","schema_version":"1.0","canonical_sha256":"49a9877f5c91dff685d88a981b818a1104d5b37bd30d7701bf742189095c4d9a","source":{"kind":"arxiv","id":"2501.07922","version":1},"attestation_state":"computed","paper":{"title":"VENOM: Text-driven Unrestricted Adversarial Example Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoying Zhao, Haoyu Chen, Hui Kuurila-Zhang","submitted_at":"2025-01-14T08:12:20Z","abstract_excerpt":"Adversarial attacks have proven effective in deceiving machine learning models by subtly altering input images, motivating extensive research in recent years. Traditional methods constrain perturbations within $l_p$-norm bounds, but advancements in Unrestricted Adversarial Examples (UAEs) allow for more complex, generative-model-based manipulations. Diffusion models now lead UAE generation due to superior stability and image quality over GANs. However, existing diffusion-based UAE methods are limited to using reference images and face challenges in generating Natural Adversarial Examples (NAEs"},"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":"2501.07922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T08:12:20Z","cross_cats_sorted":[],"title_canon_sha256":"18ede74871c81cbbc6c6138665fe9dd365e74bfc4ad83392b7fd8cec0e918987","abstract_canon_sha256":"fb1534cb69e3b27c294b2d5cb005644be605489d25fa4180c6d90c245534a666"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:52.608442Z","signature_b64":"4oNvEcSaRY7j4Ju9m8S4ZXpbx1HTI4JDf/X3alnvtc94cvixcry7cyHN9nB8VySe2XsB+jn0Y75lNfMuqww/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49a9877f5c91dff685d88a981b818a1104d5b37bd30d7701bf742189095c4d9a","last_reissued_at":"2026-07-05T10:00:52.607906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:52.607906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VENOM: Text-driven Unrestricted Adversarial Example Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoying Zhao, Haoyu Chen, Hui Kuurila-Zhang","submitted_at":"2025-01-14T08:12:20Z","abstract_excerpt":"Adversarial attacks have proven effective in deceiving machine learning models by subtly altering input images, motivating extensive research in recent years. Traditional methods constrain perturbations within $l_p$-norm bounds, but advancements in Unrestricted Adversarial Examples (UAEs) allow for more complex, generative-model-based manipulations. Diffusion models now lead UAE generation due to superior stability and image quality over GANs. However, existing diffusion-based UAE methods are limited to using reference images and face challenges in generating Natural Adversarial Examples (NAEs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07922","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/2501.07922/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":"2501.07922","created_at":"2026-07-05T10:00:52.607963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07922v1","created_at":"2026-07-05T10:00:52.607963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07922","created_at":"2026-07-05T10:00:52.607963+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGUYO724SHP7","created_at":"2026-07-05T10:00:52.607963+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGUYO724SHP7NBOY","created_at":"2026-07-05T10:00:52.607963+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGUYO724","created_at":"2026-07-05T10:00:52.607963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08734","citing_title":"IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE","json":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE.json","graph_json":"https://pith.science/api/pith-number/JGUYO724SHP7NBOYRKMBXAMKCE/graph.json","events_json":"https://pith.science/api/pith-number/JGUYO724SHP7NBOYRKMBXAMKCE/events.json","paper":"https://pith.science/paper/JGUYO724"},"agent_actions":{"view_html":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE","download_json":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE.json","view_paper":"https://pith.science/paper/JGUYO724","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07922&json=true","fetch_graph":"https://pith.science/api/pith-number/JGUYO724SHP7NBOYRKMBXAMKCE/graph.json","fetch_events":"https://pith.science/api/pith-number/JGUYO724SHP7NBOYRKMBXAMKCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE/action/storage_attestation","attest_author":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE/action/author_attestation","sign_citation":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE/action/citation_signature","submit_replication":"https://pith.science/pith/JGUYO724SHP7NBOYRKMBXAMKCE/action/replication_record"}},"created_at":"2026-07-05T10:00:52.607963+00:00","updated_at":"2026-07-05T10:00:52.607963+00:00"}