{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QEKRAMFFL7PVXVMEK7CM5TWOLK","short_pith_number":"pith:QEKRAMFF","schema_version":"1.0","canonical_sha256":"81151030a55fdf5bd58457c4cecece5abdd187dc86f4487b8e226b810695c998","source":{"kind":"arxiv","id":"2312.13628","version":2},"attestation_state":"computed","paper":{"title":"Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furui Liu, Jie Qiao, Ruichu Cai, Yuxuan Zhu, Zefeng Liang, Zhifeng Hao","submitted_at":"2023-12-21T07:38:59Z","abstract_excerpt":"Deep neural networks (DNNs) have been demonstrated to be vulnerable to well-crafted \\emph{adversarial examples}, which are generated through either well-conceived $\\mathcal{L}_p$-norm restricted or unrestricted attacks. Nevertheless, the majority of those approaches assume that adversaries can modify any features as they wish, and neglect the causal generating process of the data, which is unreasonable and unpractical. For instance, a modification in income would inevitably impact features like the debt-to-income ratio within a banking system. By considering the underappreciated causal generat"},"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":"2312.13628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-21T07:38:59Z","cross_cats_sorted":[],"title_canon_sha256":"8d25be0b12832d80c23c12fddafe21ccac64e284e13fa62a92910d955d6f2b77","abstract_canon_sha256":"53398d6499e5bf8c349ce08b2ddae0638f650e800c96564e98c2098a3332e036"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:54.393176Z","signature_b64":"Z6uDFzJQRssN5mcyxF47M9Be9YAtqklbd+6WQvRlc5aHx8YYC4vU8CF1ODs2Egvu2NBhFz3Jc25w9LuSTIWTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81151030a55fdf5bd58457c4cecece5abdd187dc86f4487b8e226b810695c998","last_reissued_at":"2026-07-05T07:37:54.392709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:54.392709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furui Liu, Jie Qiao, Ruichu Cai, Yuxuan Zhu, Zefeng Liang, Zhifeng Hao","submitted_at":"2023-12-21T07:38:59Z","abstract_excerpt":"Deep neural networks (DNNs) have been demonstrated to be vulnerable to well-crafted \\emph{adversarial examples}, which are generated through either well-conceived $\\mathcal{L}_p$-norm restricted or unrestricted attacks. Nevertheless, the majority of those approaches assume that adversaries can modify any features as they wish, and neglect the causal generating process of the data, which is unreasonable and unpractical. For instance, a modification in income would inevitably impact features like the debt-to-income ratio within a banking system. By considering the underappreciated causal generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13628","kind":"arxiv","version":2},"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/2312.13628/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":"2312.13628","created_at":"2026-07-05T07:37:54.392771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13628v2","created_at":"2026-07-05T07:37:54.392771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13628","created_at":"2026-07-05T07:37:54.392771+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEKRAMFFL7PV","created_at":"2026-07-05T07:37:54.392771+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEKRAMFFL7PVXVME","created_at":"2026-07-05T07:37:54.392771+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEKRAMFF","created_at":"2026-07-05T07:37:54.392771+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/QEKRAMFFL7PVXVMEK7CM5TWOLK","json":"https://pith.science/pith/QEKRAMFFL7PVXVMEK7CM5TWOLK.json","graph_json":"https://pith.science/api/pith-number/QEKRAMFFL7PVXVMEK7CM5TWOLK/graph.json","events_json":"https://pith.science/api/pith-number/QEKRAMFFL7PVXVMEK7CM5TWOLK/events.json","paper":"https://pith.science/paper/QEKRAMFF"},"agent_actions":{"view_html":"https://pith.science/pith/QEKRAMFFL7PVXVMEK7CM5TWOLK","download_json":"https://pith.science/pith/QEKRAMFFL7PVXVMEK7CM5TWOLK.json","view_paper":"https://pith.science/paper/QEKRAMFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13628&json=true","fetch_graph":"https://pith.science/api/pith-number/QEKRAMFFL7PVXVMEK7CM5TWOLK/graph.json","fetch_events":"https://pith.science/api/pith-number/QEKRAMFFL7PVXVMEK7CM5TWOLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEKRAMFFL7PVXVMEK7CM5TWOLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEKRAMFFL7PVXVMEK7CM5TWOLK/action/storage_attestation","attest_author":"https://pith.science/pith/QEKRAMFFL7PVXVMEK7CM5TWOLK/action/author_attestation","sign_citation":"https://pith.science/pith/QEKRAMFFL7PVXVMEK7CM5TWOLK/action/citation_signature","submit_replication":"https://pith.science/pith/QEKRAMFFL7PVXVMEK7CM5TWOLK/action/replication_record"}},"created_at":"2026-07-05T07:37:54.392771+00:00","updated_at":"2026-07-05T07:37:54.392771+00:00"}