{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SOA24WEW7UPHWH6M7KWKVLXDZN","short_pith_number":"pith:SOA24WEW","schema_version":"1.0","canonical_sha256":"9381ae5896fd1e7b1fccfaacaaaee3cb4cde54f60a220cf146445103463389c2","source":{"kind":"arxiv","id":"2211.11236","version":3},"attestation_state":"computed","paper":{"title":"Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Dingkang Yang, Haijing Guo, Jiafeng Wang, Kaixun Jiang, Lingyi Hong, Pinxue Guo, Wenqiang Zhang, Zhaoyu Chen","submitted_at":"2022-11-21T07:59:22Z","abstract_excerpt":"Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across models, enabling practical black-box attacks. However, existing methods are still incapable of achieving the desired transfer attack performance. In this work, focusing on gradient optimization and consistency, we analyse the gradient elimination phenomenon as well as the local momentum optimum dilemma. To tackle these challenges, we introduce Global Momentum Initialization (GI"},"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":"2211.11236","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T07:59:22Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"034fc1f4f28ce491614e237aace134441e2c760a58e278eb53bd8fbe9e968c18","abstract_canon_sha256":"cda1fe939d156e9f9e880052791f9a05088181b65d75d342442e27b64e17193d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:08.185405Z","signature_b64":"kwtjV1oibRW6q/b4pSoHei2SFQ79PiUlUDKeoBhuXI9wLcOO/4d+S7djfbT/KUCiZzJxlSyuyANJ1HtamDjMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9381ae5896fd1e7b1fccfaacaaaee3cb4cde54f60a220cf146445103463389c2","last_reissued_at":"2026-07-05T08:44:08.184969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:08.184969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Dingkang Yang, Haijing Guo, Jiafeng Wang, Kaixun Jiang, Lingyi Hong, Pinxue Guo, Wenqiang Zhang, Zhaoyu Chen","submitted_at":"2022-11-21T07:59:22Z","abstract_excerpt":"Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across models, enabling practical black-box attacks. However, existing methods are still incapable of achieving the desired transfer attack performance. In this work, focusing on gradient optimization and consistency, we analyse the gradient elimination phenomenon as well as the local momentum optimum dilemma. To tackle these challenges, we introduce Global Momentum Initialization (GI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11236","kind":"arxiv","version":3},"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/2211.11236/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":"2211.11236","created_at":"2026-07-05T08:44:08.185021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11236v3","created_at":"2026-07-05T08:44:08.185021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11236","created_at":"2026-07-05T08:44:08.185021+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOA24WEW7UPH","created_at":"2026-07-05T08:44:08.185021+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOA24WEW7UPHWH6M","created_at":"2026-07-05T08:44:08.185021+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOA24WEW","created_at":"2026-07-05T08:44:08.185021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16052","citing_title":"Disrupting Semantic and Abstract Features for Better Adversarial Transferability","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN","json":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN.json","graph_json":"https://pith.science/api/pith-number/SOA24WEW7UPHWH6M7KWKVLXDZN/graph.json","events_json":"https://pith.science/api/pith-number/SOA24WEW7UPHWH6M7KWKVLXDZN/events.json","paper":"https://pith.science/paper/SOA24WEW"},"agent_actions":{"view_html":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN","download_json":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN.json","view_paper":"https://pith.science/paper/SOA24WEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11236&json=true","fetch_graph":"https://pith.science/api/pith-number/SOA24WEW7UPHWH6M7KWKVLXDZN/graph.json","fetch_events":"https://pith.science/api/pith-number/SOA24WEW7UPHWH6M7KWKVLXDZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN/action/storage_attestation","attest_author":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN/action/author_attestation","sign_citation":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN/action/citation_signature","submit_replication":"https://pith.science/pith/SOA24WEW7UPHWH6M7KWKVLXDZN/action/replication_record"}},"created_at":"2026-07-05T08:44:08.185021+00:00","updated_at":"2026-07-05T08:44:08.185021+00:00"}