{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2JU22LVJOI5HMQCCLZATBZ74VG","short_pith_number":"pith:2JU22LVJ","schema_version":"1.0","canonical_sha256":"d269ad2ea9723a7640425e4130e7fca985217100cefb240bea22ffcb4cdf336a","source":{"kind":"arxiv","id":"2006.05097","version":1},"attestation_state":"computed","paper":{"title":"GAP++: Learning to generate target-conditioned adversarial examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hui Xue, Xiaofeng Mao, Yuan He, Yuefeng Chen, Yuhong Li","submitted_at":"2020-06-09T07:49:49Z","abstract_excerpt":"Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency, recent works use adversarial generative networks to model the distribution of both the universal or image-dependent perturbations directly. However, these methods generate perturbations only rely on input images. In this work, we propose a more general-purpose framework which infers target-conditioned perturbations dependent on both input image and target labe"},"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":"2006.05097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-09T07:49:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"17519526e31ff45deb0b885a7f2fac4ccb2a986e2b2c996ba23b72add1a5ac29","abstract_canon_sha256":"971cb9cbe64f80fba8742324ac8403fde608cfb23068c3a991a6c0454ae64237"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:10.560114Z","signature_b64":"RI2EvdVSLZoAqAN3zVzPx8BRtIX6FD9gRYwcV4yweCINuDhGIWnUWhNDX8FQU6wcet0h8kfJIE2KxVsdTkq4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d269ad2ea9723a7640425e4130e7fca985217100cefb240bea22ffcb4cdf336a","last_reissued_at":"2026-07-05T01:09:10.559570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:10.559570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAP++: Learning to generate target-conditioned adversarial examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hui Xue, Xiaofeng Mao, Yuan He, Yuefeng Chen, Yuhong Li","submitted_at":"2020-06-09T07:49:49Z","abstract_excerpt":"Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency, recent works use adversarial generative networks to model the distribution of both the universal or image-dependent perturbations directly. However, these methods generate perturbations only rely on input images. In this work, we propose a more general-purpose framework which infers target-conditioned perturbations dependent on both input image and target labe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05097","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/2006.05097/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":"2006.05097","created_at":"2026-07-05T01:09:10.559634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.05097v1","created_at":"2026-07-05T01:09:10.559634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05097","created_at":"2026-07-05T01:09:10.559634+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JU22LVJOI5H","created_at":"2026-07-05T01:09:10.559634+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JU22LVJOI5HMQCC","created_at":"2026-07-05T01:09:10.559634+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JU22LVJ","created_at":"2026-07-05T01:09:10.559634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG","json":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG.json","graph_json":"https://pith.science/api/pith-number/2JU22LVJOI5HMQCCLZATBZ74VG/graph.json","events_json":"https://pith.science/api/pith-number/2JU22LVJOI5HMQCCLZATBZ74VG/events.json","paper":"https://pith.science/paper/2JU22LVJ"},"agent_actions":{"view_html":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG","download_json":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG.json","view_paper":"https://pith.science/paper/2JU22LVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.05097&json=true","fetch_graph":"https://pith.science/api/pith-number/2JU22LVJOI5HMQCCLZATBZ74VG/graph.json","fetch_events":"https://pith.science/api/pith-number/2JU22LVJOI5HMQCCLZATBZ74VG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG/action/storage_attestation","attest_author":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG/action/author_attestation","sign_citation":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG/action/citation_signature","submit_replication":"https://pith.science/pith/2JU22LVJOI5HMQCCLZATBZ74VG/action/replication_record"}},"created_at":"2026-07-05T01:09:10.559634+00:00","updated_at":"2026-07-05T01:09:10.559634+00:00"}