{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JAZDPD4DVRYFIV5HS4XFV33Z3D","short_pith_number":"pith:JAZDPD4D","schema_version":"1.0","canonical_sha256":"4832378f83ac705457a7972e5aef79d8ebd2a053fd4de8c7daf20e930bcc8681","source":{"kind":"arxiv","id":"2507.01791","version":1},"attestation_state":"computed","paper":{"title":"Boosting Adversarial Transferability Against Defenses via Multi-Scale Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wan, Hailing Kuang, Xiaohai Lu, Yayin Zheng, Zihong Guo","submitted_at":"2025-07-02T15:16:30Z","abstract_excerpt":"The transferability of adversarial examples poses a significant security challenge for deep neural networks, which can be attacked without knowing anything about them. In this paper, we propose a new Segmented Gaussian Pyramid (SGP) attack method to enhance the transferability, particularly against defense models. Unlike existing methods that generally focus on single-scale images, our approach employs Gaussian filtering and three types of downsampling to construct a series of multi-scale examples. Then, the gradients of the loss function with respect to each scale are computed, and their aver"},"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":"2507.01791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T15:16:30Z","cross_cats_sorted":[],"title_canon_sha256":"7d148087ca1d0367bd3047c9a9c6a93dad1f3a31b8e348a87a9320cd81911a35","abstract_canon_sha256":"bb469b112e3dcf0d0a9ed12e13bfd29c756f3044c9161f036fd7d80b59d1b05d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:55.125399Z","signature_b64":"1Hj98gZakgTmnbJs0vhJq6qdHJicnw2ERc74zfYKzyU5X5VKE2AtH8bYKMjFzXZJhKqxcU0+ri8NUI6MWBrBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4832378f83ac705457a7972e5aef79d8ebd2a053fd4de8c7daf20e930bcc8681","last_reissued_at":"2026-07-05T11:30:55.124877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:55.124877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Adversarial Transferability Against Defenses via Multi-Scale Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wan, Hailing Kuang, Xiaohai Lu, Yayin Zheng, Zihong Guo","submitted_at":"2025-07-02T15:16:30Z","abstract_excerpt":"The transferability of adversarial examples poses a significant security challenge for deep neural networks, which can be attacked without knowing anything about them. In this paper, we propose a new Segmented Gaussian Pyramid (SGP) attack method to enhance the transferability, particularly against defense models. Unlike existing methods that generally focus on single-scale images, our approach employs Gaussian filtering and three types of downsampling to construct a series of multi-scale examples. Then, the gradients of the loss function with respect to each scale are computed, and their aver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01791","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/2507.01791/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":"2507.01791","created_at":"2026-07-05T11:30:55.124937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01791v1","created_at":"2026-07-05T11:30:55.124937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01791","created_at":"2026-07-05T11:30:55.124937+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAZDPD4DVRYF","created_at":"2026-07-05T11:30:55.124937+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAZDPD4DVRYFIV5H","created_at":"2026-07-05T11:30:55.124937+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAZDPD4D","created_at":"2026-07-05T11:30:55.124937+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/JAZDPD4DVRYFIV5HS4XFV33Z3D","json":"https://pith.science/pith/JAZDPD4DVRYFIV5HS4XFV33Z3D.json","graph_json":"https://pith.science/api/pith-number/JAZDPD4DVRYFIV5HS4XFV33Z3D/graph.json","events_json":"https://pith.science/api/pith-number/JAZDPD4DVRYFIV5HS4XFV33Z3D/events.json","paper":"https://pith.science/paper/JAZDPD4D"},"agent_actions":{"view_html":"https://pith.science/pith/JAZDPD4DVRYFIV5HS4XFV33Z3D","download_json":"https://pith.science/pith/JAZDPD4DVRYFIV5HS4XFV33Z3D.json","view_paper":"https://pith.science/paper/JAZDPD4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01791&json=true","fetch_graph":"https://pith.science/api/pith-number/JAZDPD4DVRYFIV5HS4XFV33Z3D/graph.json","fetch_events":"https://pith.science/api/pith-number/JAZDPD4DVRYFIV5HS4XFV33Z3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAZDPD4DVRYFIV5HS4XFV33Z3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAZDPD4DVRYFIV5HS4XFV33Z3D/action/storage_attestation","attest_author":"https://pith.science/pith/JAZDPD4DVRYFIV5HS4XFV33Z3D/action/author_attestation","sign_citation":"https://pith.science/pith/JAZDPD4DVRYFIV5HS4XFV33Z3D/action/citation_signature","submit_replication":"https://pith.science/pith/JAZDPD4DVRYFIV5HS4XFV33Z3D/action/replication_record"}},"created_at":"2026-07-05T11:30:55.124937+00:00","updated_at":"2026-07-05T11:30:55.124937+00:00"}