{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4MQRCDM6NOY3X4FRSYWN5CS5DU","short_pith_number":"pith:4MQRCDM6","schema_version":"1.0","canonical_sha256":"e321110d9e6bb1bbf0b1962cde8a5d1d09856a4d82e9192374984dfb7c1c672e","source":{"kind":"arxiv","id":"2505.21181","version":1},"attestation_state":"computed","paper":{"title":"Boosting Adversarial Transferability via High-Frequency Augmentation and Hierarchical-Gradient Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chen Wan, Hailing Kuang, Xiaohai Lu, Yayin Zheng, Zihong Guo","submitted_at":"2025-05-27T13:32:52Z","abstract_excerpt":"Adversarial attacks have become a significant challenge in the security of machine learning models, particularly in the context of black-box defense strategies. Existing methods for enhancing adversarial transferability primarily focus on the spatial domain. This paper presents Frequency-Space Attack (FSA), a new adversarial attack framework that effectively integrates frequency-domain and spatial-domain transformations. FSA combines two key techniques: (1) High-Frequency Augmentation, which applies Fourier transform with frequency-selective amplification to diversify inputs and emphasize the "},"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":"2505.21181","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T13:32:52Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"add841c3a43ba714809a98ca8c9eeb5fe20e58a2918d9ad1ca231287121aafb8","abstract_canon_sha256":"4aa1d65f61266bec67e7a5b6b9d4f9c7ec7c62bc98cc9d1ce68a3e0f44855f87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:25.121782Z","signature_b64":"2Qkbcp/JmtdkF13tqf0ljJm99NonuH3XkACIKFXpTp2u1KWvQake5mjrc5ptgI8eqf60ybBRX+ta3lC7a4j7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e321110d9e6bb1bbf0b1962cde8a5d1d09856a4d82e9192374984dfb7c1c672e","last_reissued_at":"2026-07-05T11:10:25.121347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:25.121347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Adversarial Transferability via High-Frequency Augmentation and Hierarchical-Gradient Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chen Wan, Hailing Kuang, Xiaohai Lu, Yayin Zheng, Zihong Guo","submitted_at":"2025-05-27T13:32:52Z","abstract_excerpt":"Adversarial attacks have become a significant challenge in the security of machine learning models, particularly in the context of black-box defense strategies. Existing methods for enhancing adversarial transferability primarily focus on the spatial domain. This paper presents Frequency-Space Attack (FSA), a new adversarial attack framework that effectively integrates frequency-domain and spatial-domain transformations. FSA combines two key techniques: (1) High-Frequency Augmentation, which applies Fourier transform with frequency-selective amplification to diversify inputs and emphasize the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21181","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/2505.21181/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":"2505.21181","created_at":"2026-07-05T11:10:25.121403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21181v1","created_at":"2026-07-05T11:10:25.121403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21181","created_at":"2026-07-05T11:10:25.121403+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MQRCDM6NOY3","created_at":"2026-07-05T11:10:25.121403+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MQRCDM6NOY3X4FR","created_at":"2026-07-05T11:10:25.121403+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MQRCDM6","created_at":"2026-07-05T11:10:25.121403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21541","citing_title":"Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU","json":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU.json","graph_json":"https://pith.science/api/pith-number/4MQRCDM6NOY3X4FRSYWN5CS5DU/graph.json","events_json":"https://pith.science/api/pith-number/4MQRCDM6NOY3X4FRSYWN5CS5DU/events.json","paper":"https://pith.science/paper/4MQRCDM6"},"agent_actions":{"view_html":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU","download_json":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU.json","view_paper":"https://pith.science/paper/4MQRCDM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21181&json=true","fetch_graph":"https://pith.science/api/pith-number/4MQRCDM6NOY3X4FRSYWN5CS5DU/graph.json","fetch_events":"https://pith.science/api/pith-number/4MQRCDM6NOY3X4FRSYWN5CS5DU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU/action/storage_attestation","attest_author":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU/action/author_attestation","sign_citation":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU/action/citation_signature","submit_replication":"https://pith.science/pith/4MQRCDM6NOY3X4FRSYWN5CS5DU/action/replication_record"}},"created_at":"2026-07-05T11:10:25.121403+00:00","updated_at":"2026-07-05T11:10:25.121403+00:00"}