{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F5X2JCNLMPDZBGQSPLN2LJRDMH","short_pith_number":"pith:F5X2JCNL","schema_version":"1.0","canonical_sha256":"2f6fa489ab63c7909a127adba5a62361ead0e695eec37b1af9f5dccc42b1be29","source":{"kind":"arxiv","id":"2401.13205","version":1},"attestation_state":"computed","paper":{"title":"Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Junlin Liu, Xinchen Lyu","submitted_at":"2024-01-24T03:26:34Z","abstract_excerpt":"Adversarial examples are one critical security threat to various visual applications, where injected human-imperceptible perturbations can confuse the output.Generating transferable adversarial examples in the black-box setting is crucial but challenging in practice. Existing input-diversity-based methods adopt different image transformations, but may be inefficient due to insufficient input diversity and an identical perturbation step size. Motivated by the fact that different image regions have distinctive weights in classification, this paper proposes a black-box adversarial generative fram"},"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":"2401.13205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T03:26:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7aec86bcdc00b7fc060f0bcd4a35bedb99df00f3588cdc113477c250c80984fc","abstract_canon_sha256":"c35b30a543cccaf369a4410a5d637f3c381d2515c6e1ef8193cd141cb7a503f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:02.289089Z","signature_b64":"/X34fsYiBucy9s0DbupG9ckkuEvGvuWHUEJ+LX3xc+yTWmUp9F6mmrWKkYZZCFPZ7v/sbV7m+oRviG4DJr4qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f6fa489ab63c7909a127adba5a62361ead0e695eec37b1af9f5dccc42b1be29","last_reissued_at":"2026-07-05T07:37:02.288624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:02.288624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Junlin Liu, Xinchen Lyu","submitted_at":"2024-01-24T03:26:34Z","abstract_excerpt":"Adversarial examples are one critical security threat to various visual applications, where injected human-imperceptible perturbations can confuse the output.Generating transferable adversarial examples in the black-box setting is crucial but challenging in practice. Existing input-diversity-based methods adopt different image transformations, but may be inefficient due to insufficient input diversity and an identical perturbation step size. Motivated by the fact that different image regions have distinctive weights in classification, this paper proposes a black-box adversarial generative fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13205","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/2401.13205/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":"2401.13205","created_at":"2026-07-05T07:37:02.288677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13205v1","created_at":"2026-07-05T07:37:02.288677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13205","created_at":"2026-07-05T07:37:02.288677+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5X2JCNLMPDZ","created_at":"2026-07-05T07:37:02.288677+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5X2JCNLMPDZBGQS","created_at":"2026-07-05T07:37:02.288677+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5X2JCNL","created_at":"2026-07-05T07:37:02.288677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11815","citing_title":"Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH","json":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH.json","graph_json":"https://pith.science/api/pith-number/F5X2JCNLMPDZBGQSPLN2LJRDMH/graph.json","events_json":"https://pith.science/api/pith-number/F5X2JCNLMPDZBGQSPLN2LJRDMH/events.json","paper":"https://pith.science/paper/F5X2JCNL"},"agent_actions":{"view_html":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH","download_json":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH.json","view_paper":"https://pith.science/paper/F5X2JCNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13205&json=true","fetch_graph":"https://pith.science/api/pith-number/F5X2JCNLMPDZBGQSPLN2LJRDMH/graph.json","fetch_events":"https://pith.science/api/pith-number/F5X2JCNLMPDZBGQSPLN2LJRDMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH/action/storage_attestation","attest_author":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH/action/author_attestation","sign_citation":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH/action/citation_signature","submit_replication":"https://pith.science/pith/F5X2JCNLMPDZBGQSPLN2LJRDMH/action/replication_record"}},"created_at":"2026-07-05T07:37:02.288677+00:00","updated_at":"2026-07-05T07:37:02.288677+00:00"}