{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KSARS2ITIEF3B7OFSKY2K2JARQ","short_pith_number":"pith:KSARS2IT","schema_version":"1.0","canonical_sha256":"5481196913410bb0fdc592b1a569208c094fe969439021cdd70662f0e7067c6e","source":{"kind":"arxiv","id":"2104.12378","version":1},"attestation_state":"computed","paper":{"title":"Delving into Data: Effectively Substitute Training for Black-box Attack","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangjie Yin, Feiyue Huang, Jilin Li, Li Zhang, Shouhong Ding, Taiping Yao, Wenxuan Wang, Xiangyang Xue, Yanwei Fu","submitted_at":"2021-04-26T07:26:29Z","abstract_excerpt":"Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has attracted wide attention. Previous substitute training approaches focus on stealing the knowledge of the target model based on real training data or synthetic data, without exploring what kind of data can further improve the transferability between the substitute and target models. In this paper, we propose a novel perspective substitute training that focuses on "},"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":"2104.12378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-26T07:26:29Z","cross_cats_sorted":[],"title_canon_sha256":"ce0494ee1956e061e1266cfd04871ce51844993069ae2539824a6ac9f47f7136","abstract_canon_sha256":"0e4cc6b1ffb09cf5627f53c00e20c67e5b8814c523c0fd95458ae64ca85d740b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:56.251873Z","signature_b64":"4EMYtYxE1z56kWDOXSmxBxcovg35jk6xRZRk+UC0whEEbEjMnBEMJW9NC14TTSNr8Lji128dKnkO+VA9CYGwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5481196913410bb0fdc592b1a569208c094fe969439021cdd70662f0e7067c6e","last_reissued_at":"2026-07-05T02:34:56.251379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:56.251379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delving into Data: Effectively Substitute Training for Black-box Attack","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bangjie Yin, Feiyue Huang, Jilin Li, Li Zhang, Shouhong Ding, Taiping Yao, Wenxuan Wang, Xiangyang Xue, Yanwei Fu","submitted_at":"2021-04-26T07:26:29Z","abstract_excerpt":"Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has attracted wide attention. Previous substitute training approaches focus on stealing the knowledge of the target model based on real training data or synthetic data, without exploring what kind of data can further improve the transferability between the substitute and target models. In this paper, we propose a novel perspective substitute training that focuses on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12378","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/2104.12378/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":"2104.12378","created_at":"2026-07-05T02:34:56.251445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.12378v1","created_at":"2026-07-05T02:34:56.251445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12378","created_at":"2026-07-05T02:34:56.251445+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSARS2ITIEF3","created_at":"2026-07-05T02:34:56.251445+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSARS2ITIEF3B7OF","created_at":"2026-07-05T02:34:56.251445+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSARS2IT","created_at":"2026-07-05T02:34:56.251445+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/KSARS2ITIEF3B7OFSKY2K2JARQ","json":"https://pith.science/pith/KSARS2ITIEF3B7OFSKY2K2JARQ.json","graph_json":"https://pith.science/api/pith-number/KSARS2ITIEF3B7OFSKY2K2JARQ/graph.json","events_json":"https://pith.science/api/pith-number/KSARS2ITIEF3B7OFSKY2K2JARQ/events.json","paper":"https://pith.science/paper/KSARS2IT"},"agent_actions":{"view_html":"https://pith.science/pith/KSARS2ITIEF3B7OFSKY2K2JARQ","download_json":"https://pith.science/pith/KSARS2ITIEF3B7OFSKY2K2JARQ.json","view_paper":"https://pith.science/paper/KSARS2IT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.12378&json=true","fetch_graph":"https://pith.science/api/pith-number/KSARS2ITIEF3B7OFSKY2K2JARQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KSARS2ITIEF3B7OFSKY2K2JARQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSARS2ITIEF3B7OFSKY2K2JARQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSARS2ITIEF3B7OFSKY2K2JARQ/action/storage_attestation","attest_author":"https://pith.science/pith/KSARS2ITIEF3B7OFSKY2K2JARQ/action/author_attestation","sign_citation":"https://pith.science/pith/KSARS2ITIEF3B7OFSKY2K2JARQ/action/citation_signature","submit_replication":"https://pith.science/pith/KSARS2ITIEF3B7OFSKY2K2JARQ/action/replication_record"}},"created_at":"2026-07-05T02:34:56.251445+00:00","updated_at":"2026-07-05T02:34:56.251445+00:00"}