{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2KGB6JGPWY5SUQFMOJWRU2ACQB","short_pith_number":"pith:2KGB6JGP","schema_version":"1.0","canonical_sha256":"d28c1f24cfb63b2a40ac726d1a68028054af146a1ef08a1cbe889f7de65e4173","source":{"kind":"arxiv","id":"1711.07356","version":3},"attestation_state":"computed","paper":{"title":"Evaluating Robustness of Neural Networks with Mixed Integer Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Kai Xiao, Russ Tedrake, Vincent Tjeng","submitted_at":"2017-11-20T15:05:33Z","abstract_excerpt":"Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that are misclassified with high confidence. Verification of networks enables us to gauge their vulnerability to such adversarial examples. We formulate verification of piecewise-linear neural networks as a mixed integer program. On a representative task of finding minimum adversarial distortions, our verifier is two to three orders of magnitude quicker than the s"},"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":"1711.07356","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-20T15:05:33Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"6415189dfaa7b91239111e559bed3a40fa6eb1cfe5b6be70e8ad5192fdad42ad","abstract_canon_sha256":"834949627f575162cd18a4c48fa1fbf52cecc51385bf458af0dd0e665f054797"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:51.914643Z","signature_b64":"pzp64iZwxSBFSQv2b3+PTKzmAczyG8NoGczAVJofhI4X9KNY5EMMGaNiyoXOdEyVzwgCMOzc8AZv519W+2RjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d28c1f24cfb63b2a40ac726d1a68028054af146a1ef08a1cbe889f7de65e4173","last_reissued_at":"2026-05-17T23:53:51.913958Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:51.913958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Robustness of Neural Networks with Mixed Integer Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Kai Xiao, Russ Tedrake, Vincent Tjeng","submitted_at":"2017-11-20T15:05:33Z","abstract_excerpt":"Neural networks have demonstrated considerable success on a wide variety of real-world problems. However, networks trained only to optimize for training accuracy can often be fooled by adversarial examples - slightly perturbed inputs that are misclassified with high confidence. Verification of networks enables us to gauge their vulnerability to such adversarial examples. We formulate verification of piecewise-linear neural networks as a mixed integer program. On a representative task of finding minimum adversarial distortions, our verifier is two to three orders of magnitude quicker than the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07356","kind":"arxiv","version":3},"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":"1711.07356","created_at":"2026-05-17T23:53:51.914056+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07356v3","created_at":"2026-05-17T23:53:51.914056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07356","created_at":"2026-05-17T23:53:51.914056+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KGB6JGPWY5S","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KGB6JGPWY5SUQFM","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KGB6JGP","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2410.03000","citing_title":"Towards Generalized Certified Robustness with Multi-Norm Training","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2503.22660","citing_title":"Polyhedral Enclosures: An Efficient Combinatorial Abstraction for Nonlinear Neural Feedback Systems","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17153","citing_title":"Stress-Testing Neural Network Verifiers with Provably Robust Instances","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2507.09503","citing_title":"Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2510.23867","citing_title":"Neural Two-Stage Stochastic Volt-VAR Optimization for Three-Phase Unbalanced Distribution Systems with Network Reconfiguration","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2512.07750","citing_title":"A Performance Analyzer for a Public Cloud's ML-Augmented VM Allocator","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB","json":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB.json","graph_json":"https://pith.science/api/pith-number/2KGB6JGPWY5SUQFMOJWRU2ACQB/graph.json","events_json":"https://pith.science/api/pith-number/2KGB6JGPWY5SUQFMOJWRU2ACQB/events.json","paper":"https://pith.science/paper/2KGB6JGP"},"agent_actions":{"view_html":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB","download_json":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB.json","view_paper":"https://pith.science/paper/2KGB6JGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07356&json=true","fetch_graph":"https://pith.science/api/pith-number/2KGB6JGPWY5SUQFMOJWRU2ACQB/graph.json","fetch_events":"https://pith.science/api/pith-number/2KGB6JGPWY5SUQFMOJWRU2ACQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB/action/storage_attestation","attest_author":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB/action/author_attestation","sign_citation":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB/action/citation_signature","submit_replication":"https://pith.science/pith/2KGB6JGPWY5SUQFMOJWRU2ACQB/action/replication_record"}},"created_at":"2026-05-17T23:53:51.914056+00:00","updated_at":"2026-05-17T23:53:51.914056+00:00"}