{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SBSKZ7AC2YOYK5KA7FIAYUHCPN","short_pith_number":"pith:SBSKZ7AC","schema_version":"1.0","canonical_sha256":"9064acfc02d61d857540f9500c50e27b5d3e56701511e00674a56d4ba89a7b94","source":{"kind":"arxiv","id":"1605.07262","version":2},"attestation_state":"computed","paper":{"title":"Measuring Neural Net Robustness with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aditya Nori, Antonio Criminisi, Dimitrios Vytiniotis, Leonidas Lampropoulos, Osbert Bastani, Yani Ioannou","submitted_at":"2016-05-24T02:18:21Z","abstract_excerpt":"Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net and devise a novel algorithm for approximating these metrics based on an encoding of robustness as a linear program. We show how our metrics can be used to evaluate the robustness of deep neural nets with experiments on the MNIST and CIFAR-10 datasets. Our algorithm generates more informative estimates of robustness metrics compared to estimates based on exis"},"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":"1605.07262","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-24T02:18:21Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"39d5754ce67daeee55777c049116789f264ee5e261317f238589074b23086e29","abstract_canon_sha256":"92c8ce57c32a689349d269475fd695c8427ab0c9b41592e87f30431cb4e315b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:17.876087Z","signature_b64":"xdxcYlMd36xiGHc2ZPhmVs/acq06ulpMzIo+36d5Oo3yY0lMyPTgnoFJXLRG3vTTGVNKBfwNy3+4T6OBDjVwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9064acfc02d61d857540f9500c50e27b5d3e56701511e00674a56d4ba89a7b94","last_reissued_at":"2026-05-18T00:42:17.875374Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:17.875374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Neural Net Robustness with Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Aditya Nori, Antonio Criminisi, Dimitrios Vytiniotis, Leonidas Lampropoulos, Osbert Bastani, Yani Ioannou","submitted_at":"2016-05-24T02:18:21Z","abstract_excerpt":"Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled. We propose metrics for measuring the robustness of a neural net and devise a novel algorithm for approximating these metrics based on an encoding of robustness as a linear program. We show how our metrics can be used to evaluate the robustness of deep neural nets with experiments on the MNIST and CIFAR-10 datasets. Our algorithm generates more informative estimates of robustness metrics compared to estimates based on exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07262","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":""},"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":"1605.07262","created_at":"2026-05-18T00:42:17.875476+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.07262v2","created_at":"2026-05-18T00:42:17.875476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07262","created_at":"2026-05-18T00:42:17.875476+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBSKZ7AC2YOY","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBSKZ7AC2YOYK5KA","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBSKZ7AC","created_at":"2026-05-18T12:30:44.179134+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/SBSKZ7AC2YOYK5KA7FIAYUHCPN","json":"https://pith.science/pith/SBSKZ7AC2YOYK5KA7FIAYUHCPN.json","graph_json":"https://pith.science/api/pith-number/SBSKZ7AC2YOYK5KA7FIAYUHCPN/graph.json","events_json":"https://pith.science/api/pith-number/SBSKZ7AC2YOYK5KA7FIAYUHCPN/events.json","paper":"https://pith.science/paper/SBSKZ7AC"},"agent_actions":{"view_html":"https://pith.science/pith/SBSKZ7AC2YOYK5KA7FIAYUHCPN","download_json":"https://pith.science/pith/SBSKZ7AC2YOYK5KA7FIAYUHCPN.json","view_paper":"https://pith.science/paper/SBSKZ7AC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.07262&json=true","fetch_graph":"https://pith.science/api/pith-number/SBSKZ7AC2YOYK5KA7FIAYUHCPN/graph.json","fetch_events":"https://pith.science/api/pith-number/SBSKZ7AC2YOYK5KA7FIAYUHCPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBSKZ7AC2YOYK5KA7FIAYUHCPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBSKZ7AC2YOYK5KA7FIAYUHCPN/action/storage_attestation","attest_author":"https://pith.science/pith/SBSKZ7AC2YOYK5KA7FIAYUHCPN/action/author_attestation","sign_citation":"https://pith.science/pith/SBSKZ7AC2YOYK5KA7FIAYUHCPN/action/citation_signature","submit_replication":"https://pith.science/pith/SBSKZ7AC2YOYK5KA7FIAYUHCPN/action/replication_record"}},"created_at":"2026-05-18T00:42:17.875476+00:00","updated_at":"2026-05-18T00:42:17.875476+00:00"}