{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:36AAHWJ7XY3DBDTT7OZEIV6U4Y","short_pith_number":"pith:36AAHWJ7","schema_version":"1.0","canonical_sha256":"df8003d93fbe36308e73fbb24457d4e616d7e3d28fd865a4278358ea089caad3","source":{"kind":"arxiv","id":"1712.08250","version":1},"attestation_state":"computed","paper":{"title":"ReabsNet: Detecting and Revising Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Changtian Sun, Jiefeng Chen, Wei Tang, Yinglun Zhu, Zihang Meng","submitted_at":"2017-12-21T23:24:37Z","abstract_excerpt":"Though deep neural network has hit a huge success in recent studies and applica- tions, it still remains vulnerable to adversarial perturbations which are imperceptible to humans. To address this problem, we propose a novel network called ReabsNet to achieve high classification accuracy in the face of various attacks. The approach is to augment an existing classification network with a guardian network to detect if a sample is natural or has been adversarially perturbed. Critically, instead of simply rejecting adversarial examples, we revise them to get their true labels. We exploit the observ"},"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":"1712.08250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-21T23:24:37Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"69957ab504bcc622baf1fb1bbc275bcca83a30e4ac8e82e058ad1782d8c4376e","abstract_canon_sha256":"f4d84335de6917088605a6bab72f655df2d62f7ff66ceafbe58424ec3744d843"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:24.012023Z","signature_b64":"DFRCKAlSuUQ0nC/clMdcLOSr9vgHCWiuV6WRWOSBse48Fx2H+jR6s4OEfK1P9JFz4TcO7e/ZLkkDaf4Kt6r+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df8003d93fbe36308e73fbb24457d4e616d7e3d28fd865a4278358ea089caad3","last_reissued_at":"2026-05-18T00:27:24.011496Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:24.011496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReabsNet: Detecting and Revising Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Changtian Sun, Jiefeng Chen, Wei Tang, Yinglun Zhu, Zihang Meng","submitted_at":"2017-12-21T23:24:37Z","abstract_excerpt":"Though deep neural network has hit a huge success in recent studies and applica- tions, it still remains vulnerable to adversarial perturbations which are imperceptible to humans. To address this problem, we propose a novel network called ReabsNet to achieve high classification accuracy in the face of various attacks. The approach is to augment an existing classification network with a guardian network to detect if a sample is natural or has been adversarially perturbed. Critically, instead of simply rejecting adversarial examples, we revise them to get their true labels. We exploit the observ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08250","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":""},"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":"1712.08250","created_at":"2026-05-18T00:27:24.011587+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.08250v1","created_at":"2026-05-18T00:27:24.011587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08250","created_at":"2026-05-18T00:27:24.011587+00:00"},{"alias_kind":"pith_short_12","alias_value":"36AAHWJ7XY3D","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"36AAHWJ7XY3DBDTT","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"36AAHWJ7","created_at":"2026-05-18T12:30:58.224056+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/36AAHWJ7XY3DBDTT7OZEIV6U4Y","json":"https://pith.science/pith/36AAHWJ7XY3DBDTT7OZEIV6U4Y.json","graph_json":"https://pith.science/api/pith-number/36AAHWJ7XY3DBDTT7OZEIV6U4Y/graph.json","events_json":"https://pith.science/api/pith-number/36AAHWJ7XY3DBDTT7OZEIV6U4Y/events.json","paper":"https://pith.science/paper/36AAHWJ7"},"agent_actions":{"view_html":"https://pith.science/pith/36AAHWJ7XY3DBDTT7OZEIV6U4Y","download_json":"https://pith.science/pith/36AAHWJ7XY3DBDTT7OZEIV6U4Y.json","view_paper":"https://pith.science/paper/36AAHWJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.08250&json=true","fetch_graph":"https://pith.science/api/pith-number/36AAHWJ7XY3DBDTT7OZEIV6U4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/36AAHWJ7XY3DBDTT7OZEIV6U4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36AAHWJ7XY3DBDTT7OZEIV6U4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36AAHWJ7XY3DBDTT7OZEIV6U4Y/action/storage_attestation","attest_author":"https://pith.science/pith/36AAHWJ7XY3DBDTT7OZEIV6U4Y/action/author_attestation","sign_citation":"https://pith.science/pith/36AAHWJ7XY3DBDTT7OZEIV6U4Y/action/citation_signature","submit_replication":"https://pith.science/pith/36AAHWJ7XY3DBDTT7OZEIV6U4Y/action/replication_record"}},"created_at":"2026-05-18T00:27:24.011587+00:00","updated_at":"2026-05-18T00:27:24.011587+00:00"}