{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4WM7LMZFACHWYZTBA2WUETMVWW","short_pith_number":"pith:4WM7LMZF","schema_version":"1.0","canonical_sha256":"e599f5b325008f6c666106ad424d95b58db1af20d3aa27949482edc2978de81a","source":{"kind":"arxiv","id":"1810.08640","version":1},"attestation_state":"computed","paper":{"title":"On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelie Lozano, Cho-Jui Hsieh, Huan Zhang, Luca Daniel, Pin-Yu Chen, Tsui-Wei Weng","submitted_at":"2018-10-19T18:44:58Z","abstract_excerpt":"CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we propose two extensions on this robustness score. First, we provide a new formal robustness guarantee for classifier functions that are twice differentiable. We apply extreme value theory on the new formal robustness guarantee and the estimated robustness is called second-order CLEVER score. Second, we discuss how to handle gradient masking, a common defensive technique, using CLEVER with Backward Pass Differentiable"},"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":"1810.08640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-19T18:44:58Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"8b241e692227bb426ff2d02398c90d6b75d7d4e33be6ad79a4abf9d644bd2d14","abstract_canon_sha256":"cfb7dc2ad6a591e6baa4b70dfd9245455be97dc17ef1f9e4a5679b156266d2a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:43.951937Z","signature_b64":"eI3l2gzTeh6nSoOLyGv9h99pz7O7o1aLUaOIuM5ZkQO7taFRixcFh/kWMLwmEMmETmfwypssBUguopGo7D7sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e599f5b325008f6c666106ad424d95b58db1af20d3aa27949482edc2978de81a","last_reissued_at":"2026-05-18T00:02:43.951506Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:43.951506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelie Lozano, Cho-Jui Hsieh, Huan Zhang, Luca Daniel, Pin-Yu Chen, Tsui-Wei Weng","submitted_at":"2018-10-19T18:44:58Z","abstract_excerpt":"CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we propose two extensions on this robustness score. First, we provide a new formal robustness guarantee for classifier functions that are twice differentiable. We apply extreme value theory on the new formal robustness guarantee and the estimated robustness is called second-order CLEVER score. Second, we discuss how to handle gradient masking, a common defensive technique, using CLEVER with Backward Pass Differentiable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08640","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":"1810.08640","created_at":"2026-05-18T00:02:43.951569+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.08640v1","created_at":"2026-05-18T00:02:43.951569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08640","created_at":"2026-05-18T00:02:43.951569+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WM7LMZFACHW","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WM7LMZFACHWYZTB","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WM7LMZF","created_at":"2026-05-18T12:32:05.422762+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/4WM7LMZFACHWYZTBA2WUETMVWW","json":"https://pith.science/pith/4WM7LMZFACHWYZTBA2WUETMVWW.json","graph_json":"https://pith.science/api/pith-number/4WM7LMZFACHWYZTBA2WUETMVWW/graph.json","events_json":"https://pith.science/api/pith-number/4WM7LMZFACHWYZTBA2WUETMVWW/events.json","paper":"https://pith.science/paper/4WM7LMZF"},"agent_actions":{"view_html":"https://pith.science/pith/4WM7LMZFACHWYZTBA2WUETMVWW","download_json":"https://pith.science/pith/4WM7LMZFACHWYZTBA2WUETMVWW.json","view_paper":"https://pith.science/paper/4WM7LMZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.08640&json=true","fetch_graph":"https://pith.science/api/pith-number/4WM7LMZFACHWYZTBA2WUETMVWW/graph.json","fetch_events":"https://pith.science/api/pith-number/4WM7LMZFACHWYZTBA2WUETMVWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WM7LMZFACHWYZTBA2WUETMVWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WM7LMZFACHWYZTBA2WUETMVWW/action/storage_attestation","attest_author":"https://pith.science/pith/4WM7LMZFACHWYZTBA2WUETMVWW/action/author_attestation","sign_citation":"https://pith.science/pith/4WM7LMZFACHWYZTBA2WUETMVWW/action/citation_signature","submit_replication":"https://pith.science/pith/4WM7LMZFACHWYZTBA2WUETMVWW/action/replication_record"}},"created_at":"2026-05-18T00:02:43.951569+00:00","updated_at":"2026-05-18T00:02:43.951569+00:00"}