{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OP5O22I2XRRLVQI4KQYMGI372G","short_pith_number":"pith:OP5O22I2","schema_version":"1.0","canonical_sha256":"73faed691abc62bac11c5430c3237fd1bf8bb8d8f215e0b4dd1ed668dcf455e5","source":{"kind":"arxiv","id":"2204.00972","version":1},"attestation_state":"computed","paper":{"title":"DST: Dynamic Substitute Training for Data-free Black-box Attack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenxuan Wang, Xiangyang Xue, Xuelin Qian, Yanwei Fu","submitted_at":"2022-04-03T02:29:11Z","abstract_excerpt":"With the wide applications of deep neural network models in various computer vision tasks, more and more works study the model vulnerability to adversarial examples. For data-free black box attack scenario, existing methods are inspired by the knowledge distillation, and thus usually train a substitute model to learn knowledge from the target model using generated data as input. However, the substitute model always has a static network structure, which limits the attack ability for various target models and tasks. In this paper, we propose a novel dynamic substitute training attack method to e"},"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":"2204.00972","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-03T02:29:11Z","cross_cats_sorted":[],"title_canon_sha256":"f68453e3ea7896e301e40e17b931feb6cf04cae9bed2d20a1c01e98d7537b810","abstract_canon_sha256":"2e668518cca7d4bc165ff2651d5424ef59c6dbcbac5f210654a92277948e7683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:13.932067Z","signature_b64":"MCNGKARKZsjGu1c9vk85sGKirYgDRVR7tafhMBtNmtYUOSrIkuMQosHmOJ+iZ6SGGRu1JZ2GRNKISLngoqrqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73faed691abc62bac11c5430c3237fd1bf8bb8d8f215e0b4dd1ed668dcf455e5","last_reissued_at":"2026-07-05T04:11:13.931604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:13.931604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DST: Dynamic Substitute Training for Data-free Black-box Attack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wenxuan Wang, Xiangyang Xue, Xuelin Qian, Yanwei Fu","submitted_at":"2022-04-03T02:29:11Z","abstract_excerpt":"With the wide applications of deep neural network models in various computer vision tasks, more and more works study the model vulnerability to adversarial examples. For data-free black box attack scenario, existing methods are inspired by the knowledge distillation, and thus usually train a substitute model to learn knowledge from the target model using generated data as input. However, the substitute model always has a static network structure, which limits the attack ability for various target models and tasks. In this paper, we propose a novel dynamic substitute training attack method to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00972","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/2204.00972/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":"2204.00972","created_at":"2026-07-05T04:11:13.931673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.00972v1","created_at":"2026-07-05T04:11:13.931673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00972","created_at":"2026-07-05T04:11:13.931673+00:00"},{"alias_kind":"pith_short_12","alias_value":"OP5O22I2XRRL","created_at":"2026-07-05T04:11:13.931673+00:00"},{"alias_kind":"pith_short_16","alias_value":"OP5O22I2XRRLVQI4","created_at":"2026-07-05T04:11:13.931673+00:00"},{"alias_kind":"pith_short_8","alias_value":"OP5O22I2","created_at":"2026-07-05T04:11:13.931673+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/OP5O22I2XRRLVQI4KQYMGI372G","json":"https://pith.science/pith/OP5O22I2XRRLVQI4KQYMGI372G.json","graph_json":"https://pith.science/api/pith-number/OP5O22I2XRRLVQI4KQYMGI372G/graph.json","events_json":"https://pith.science/api/pith-number/OP5O22I2XRRLVQI4KQYMGI372G/events.json","paper":"https://pith.science/paper/OP5O22I2"},"agent_actions":{"view_html":"https://pith.science/pith/OP5O22I2XRRLVQI4KQYMGI372G","download_json":"https://pith.science/pith/OP5O22I2XRRLVQI4KQYMGI372G.json","view_paper":"https://pith.science/paper/OP5O22I2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.00972&json=true","fetch_graph":"https://pith.science/api/pith-number/OP5O22I2XRRLVQI4KQYMGI372G/graph.json","fetch_events":"https://pith.science/api/pith-number/OP5O22I2XRRLVQI4KQYMGI372G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OP5O22I2XRRLVQI4KQYMGI372G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OP5O22I2XRRLVQI4KQYMGI372G/action/storage_attestation","attest_author":"https://pith.science/pith/OP5O22I2XRRLVQI4KQYMGI372G/action/author_attestation","sign_citation":"https://pith.science/pith/OP5O22I2XRRLVQI4KQYMGI372G/action/citation_signature","submit_replication":"https://pith.science/pith/OP5O22I2XRRLVQI4KQYMGI372G/action/replication_record"}},"created_at":"2026-07-05T04:11:13.931673+00:00","updated_at":"2026-07-05T04:11:13.931673+00:00"}