{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YYPK6JFGNOVTQAHODR2YK2AE7N","short_pith_number":"pith:YYPK6JFG","schema_version":"1.0","canonical_sha256":"c61eaf24a66bab3800ee1c75856804fb429920affa42c5645e158760a36ce45a","source":{"kind":"arxiv","id":"2401.08734","version":2},"attestation_state":"computed","paper":{"title":"Bag of Tricks to Boost Adversarial Transferability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wei Yao, Xiaosen Wang, Zeliang Zhang","submitted_at":"2024-01-16T17:42:36Z","abstract_excerpt":"Deep neural networks are widely known to be vulnerable to adversarial examples. However, vanilla adversarial examples generated under the white-box setting often exhibit low transferability across different models. Since adversarial transferability poses more severe threats to practical applications, various approaches have been proposed for better transferability, including gradient-based, input transformation-based, and model-related attacks, \\etc. In this work, we find that several tiny changes in the existing adversarial attacks can significantly affect the attack performance, \\eg, the num"},"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":"2401.08734","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-16T17:42:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d6e6731be905faaf4dde9e42e90295159c40726d71c5cdc26b2d4e4c75574ff","abstract_canon_sha256":"25feafcd86c1fc3f4ea9393279c1bfafa27a876a051a20b5428fafb8112f32ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:20.730427Z","signature_b64":"1ppp5cuF0auX+DmO1dSyd7P/2r4lkqubnJeOqUScAcC7ld3HxG9gVOU1/1k7O8sDjHUQCzvtgkt+tNtCX+CbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c61eaf24a66bab3800ee1c75856804fb429920affa42c5645e158760a36ce45a","last_reissued_at":"2026-07-05T08:46:20.729903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:20.729903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bag of Tricks to Boost Adversarial Transferability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wei Yao, Xiaosen Wang, Zeliang Zhang","submitted_at":"2024-01-16T17:42:36Z","abstract_excerpt":"Deep neural networks are widely known to be vulnerable to adversarial examples. However, vanilla adversarial examples generated under the white-box setting often exhibit low transferability across different models. Since adversarial transferability poses more severe threats to practical applications, various approaches have been proposed for better transferability, including gradient-based, input transformation-based, and model-related attacks, \\etc. In this work, we find that several tiny changes in the existing adversarial attacks can significantly affect the attack performance, \\eg, the num"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08734","kind":"arxiv","version":2},"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/2401.08734/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":"2401.08734","created_at":"2026-07-05T08:46:20.729974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08734v2","created_at":"2026-07-05T08:46:20.729974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08734","created_at":"2026-07-05T08:46:20.729974+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYPK6JFGNOVT","created_at":"2026-07-05T08:46:20.729974+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYPK6JFGNOVTQAHO","created_at":"2026-07-05T08:46:20.729974+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYPK6JFG","created_at":"2026-07-05T08:46:20.729974+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/YYPK6JFGNOVTQAHODR2YK2AE7N","json":"https://pith.science/pith/YYPK6JFGNOVTQAHODR2YK2AE7N.json","graph_json":"https://pith.science/api/pith-number/YYPK6JFGNOVTQAHODR2YK2AE7N/graph.json","events_json":"https://pith.science/api/pith-number/YYPK6JFGNOVTQAHODR2YK2AE7N/events.json","paper":"https://pith.science/paper/YYPK6JFG"},"agent_actions":{"view_html":"https://pith.science/pith/YYPK6JFGNOVTQAHODR2YK2AE7N","download_json":"https://pith.science/pith/YYPK6JFGNOVTQAHODR2YK2AE7N.json","view_paper":"https://pith.science/paper/YYPK6JFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08734&json=true","fetch_graph":"https://pith.science/api/pith-number/YYPK6JFGNOVTQAHODR2YK2AE7N/graph.json","fetch_events":"https://pith.science/api/pith-number/YYPK6JFGNOVTQAHODR2YK2AE7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYPK6JFGNOVTQAHODR2YK2AE7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYPK6JFGNOVTQAHODR2YK2AE7N/action/storage_attestation","attest_author":"https://pith.science/pith/YYPK6JFGNOVTQAHODR2YK2AE7N/action/author_attestation","sign_citation":"https://pith.science/pith/YYPK6JFGNOVTQAHODR2YK2AE7N/action/citation_signature","submit_replication":"https://pith.science/pith/YYPK6JFGNOVTQAHODR2YK2AE7N/action/replication_record"}},"created_at":"2026-07-05T08:46:20.729974+00:00","updated_at":"2026-07-05T08:46:20.729974+00:00"}