{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VUDY7KN6VIJ2KT5FI2TRTQ5QA6","short_pith_number":"pith:VUDY7KN6","schema_version":"1.0","canonical_sha256":"ad078fa9beaa13a54fa546a719c3b0078e881bcc6b50af2f56bef231e54051a0","source":{"kind":"arxiv","id":"2303.03680","version":1},"attestation_state":"computed","paper":{"title":"Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juanjuan Weng, Nicu Sebe, Shaozi Li, Zhiming Luo, Zhun Zhong","submitted_at":"2023-03-07T06:42:52Z","abstract_excerpt":"Previous works have extensively studied the transferability of adversarial samples in untargeted black-box scenarios. However, it still remains challenging to craft targeted adversarial examples with higher transferability than non-targeted ones. Recent studies reveal that the traditional Cross-Entropy (CE) loss function is insufficient to learn transferable targeted adversarial examples due to the issue of vanishing gradient. In this work, we provide a comprehensive investigation of the CE loss function and find that the logit margin between the targeted and untargeted classes will quickly ob"},"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":"2303.03680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-07T06:42:52Z","cross_cats_sorted":[],"title_canon_sha256":"c085f1a299991fa75ba594e714190e76692a898a0ffc0bf18d1e29eeff1ba5ed","abstract_canon_sha256":"249636a5e5a93484681b7f610d3deb026df2ab2e7a14fe98060cbb581a41848b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:57.624611Z","signature_b64":"P+tBGij81cjIEWzgfKesYokrbwgt2CYR+Ef4rHXPDkYPkAORSYymk4llpuHNKFPTFy68sQpa+JPmoOkRtIsTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad078fa9beaa13a54fa546a719c3b0078e881bcc6b50af2f56bef231e54051a0","last_reissued_at":"2026-07-05T05:48:57.624144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:57.624144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juanjuan Weng, Nicu Sebe, Shaozi Li, Zhiming Luo, Zhun Zhong","submitted_at":"2023-03-07T06:42:52Z","abstract_excerpt":"Previous works have extensively studied the transferability of adversarial samples in untargeted black-box scenarios. However, it still remains challenging to craft targeted adversarial examples with higher transferability than non-targeted ones. Recent studies reveal that the traditional Cross-Entropy (CE) loss function is insufficient to learn transferable targeted adversarial examples due to the issue of vanishing gradient. In this work, we provide a comprehensive investigation of the CE loss function and find that the logit margin between the targeted and untargeted classes will quickly ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03680","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/2303.03680/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":"2303.03680","created_at":"2026-07-05T05:48:57.624198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03680v1","created_at":"2026-07-05T05:48:57.624198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03680","created_at":"2026-07-05T05:48:57.624198+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUDY7KN6VIJ2","created_at":"2026-07-05T05:48:57.624198+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUDY7KN6VIJ2KT5F","created_at":"2026-07-05T05:48:57.624198+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUDY7KN6","created_at":"2026-07-05T05:48:57.624198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19944","citing_title":"A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6","json":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6.json","graph_json":"https://pith.science/api/pith-number/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/graph.json","events_json":"https://pith.science/api/pith-number/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/events.json","paper":"https://pith.science/paper/VUDY7KN6"},"agent_actions":{"view_html":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6","download_json":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6.json","view_paper":"https://pith.science/paper/VUDY7KN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03680&json=true","fetch_graph":"https://pith.science/api/pith-number/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/graph.json","fetch_events":"https://pith.science/api/pith-number/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/action/storage_attestation","attest_author":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/action/author_attestation","sign_citation":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/action/citation_signature","submit_replication":"https://pith.science/pith/VUDY7KN6VIJ2KT5FI2TRTQ5QA6/action/replication_record"}},"created_at":"2026-07-05T05:48:57.624198+00:00","updated_at":"2026-07-05T05:48:57.624198+00:00"}