{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQUSWVYA7XOYCBPPA3B7M5GCXJ","short_pith_number":"pith:DQUSWVYA","schema_version":"1.0","canonical_sha256":"1c292b5700fddd8105ef06c3f674c2ba67da8c3940eab058ae0666a847bfd5ce","source":{"kind":"arxiv","id":"2412.16958","version":1},"attestation_state":"computed","paper":{"title":"Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangtao Zhang, Minghui Li, Shengshan Hu, Wei Wan, Yichen Wang, Yuxuan Chou, Ziqi Zhou","submitted_at":"2024-12-22T10:34:02Z","abstract_excerpt":"As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible.\n  In this paper, we explore a novel perturbation-based method to overco"},"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":"2412.16958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-22T10:34:02Z","cross_cats_sorted":[],"title_canon_sha256":"611cb5754800ef63cf73bfa39c6cfff4de0849100bf745829af8dd4993d29a48","abstract_canon_sha256":"dafc3e39bcebb161797b65a21dcc2f11a83b4c4057e70fc81c0fa292ca43a042"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:15.467203Z","signature_b64":"bDHqSng220CK6DmDrn64cXYUTofaYCpfbs7i/mofEKhJWPdxV2tjOvcob7xklnwIoOeMlFPSYj8I4g+F0w7CAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c292b5700fddd8105ef06c3f674c2ba67da8c3940eab058ae0666a847bfd5ce","last_reissued_at":"2026-07-05T09:53:15.466732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:15.466732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangtao Zhang, Minghui Li, Shengshan Hu, Wei Wan, Yichen Wang, Yuxuan Chou, Ziqi Zhou","submitted_at":"2024-12-22T10:34:02Z","abstract_excerpt":"As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible.\n  In this paper, we explore a novel perturbation-based method to overco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16958","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/2412.16958/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":"2412.16958","created_at":"2026-07-05T09:53:15.466781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16958v1","created_at":"2026-07-05T09:53:15.466781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16958","created_at":"2026-07-05T09:53:15.466781+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQUSWVYA7XOY","created_at":"2026-07-05T09:53:15.466781+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQUSWVYA7XOYCBPP","created_at":"2026-07-05T09:53:15.466781+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQUSWVYA","created_at":"2026-07-05T09:53:15.466781+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/DQUSWVYA7XOYCBPPA3B7M5GCXJ","json":"https://pith.science/pith/DQUSWVYA7XOYCBPPA3B7M5GCXJ.json","graph_json":"https://pith.science/api/pith-number/DQUSWVYA7XOYCBPPA3B7M5GCXJ/graph.json","events_json":"https://pith.science/api/pith-number/DQUSWVYA7XOYCBPPA3B7M5GCXJ/events.json","paper":"https://pith.science/paper/DQUSWVYA"},"agent_actions":{"view_html":"https://pith.science/pith/DQUSWVYA7XOYCBPPA3B7M5GCXJ","download_json":"https://pith.science/pith/DQUSWVYA7XOYCBPPA3B7M5GCXJ.json","view_paper":"https://pith.science/paper/DQUSWVYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16958&json=true","fetch_graph":"https://pith.science/api/pith-number/DQUSWVYA7XOYCBPPA3B7M5GCXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DQUSWVYA7XOYCBPPA3B7M5GCXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQUSWVYA7XOYCBPPA3B7M5GCXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQUSWVYA7XOYCBPPA3B7M5GCXJ/action/storage_attestation","attest_author":"https://pith.science/pith/DQUSWVYA7XOYCBPPA3B7M5GCXJ/action/author_attestation","sign_citation":"https://pith.science/pith/DQUSWVYA7XOYCBPPA3B7M5GCXJ/action/citation_signature","submit_replication":"https://pith.science/pith/DQUSWVYA7XOYCBPPA3B7M5GCXJ/action/replication_record"}},"created_at":"2026-07-05T09:53:15.466781+00:00","updated_at":"2026-07-05T09:53:15.466781+00:00"}