{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3RIMGA3JB3P4DJBN3VZKFDNSO7","short_pith_number":"pith:3RIMGA3J","schema_version":"1.0","canonical_sha256":"dc50c303690edfc1a42ddd72a28db277d992715ca9e33e8a4b4839bdfdecdb8e","source":{"kind":"arxiv","id":"1908.06353","version":1},"attestation_state":"computed","paper":{"title":"Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Luca Daniel, Tsui-Wei Weng, Yuh-Shyang Wang","submitted_at":"2019-08-18T00:23:21Z","abstract_excerpt":"Deep neural networks are known to be fragile to small adversarial perturbations. This issue becomes more critical when a neural network is interconnected with a physical system in a closed loop. In this paper, we show how to combine recent works on neural network certification tools (which are mainly used in static settings such as image classification) with robust control theory to certify a neural network policy in a control loop. Specifically, we give a sufficient condition and an algorithm to ensure that the closed loop state and control constraints are satisfied when the persistent advers"},"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":"1908.06353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-18T00:23:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a6df757dbfa2e2ac8648ab6fd7bbbe3aa26be9eb7bb135406750f00c15e1e1fd","abstract_canon_sha256":"1619dcbae42dc91a18a3b93bd59cc50adeaad4a997a5051ad1638206699ef7e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:14.941605Z","signature_b64":"dwFZF5ps+0O+7T1rcmcCGcPh2xdbdA9NP7kKElkUWJuUj/ETiQ/dskwvD6fUxysQ9+q+7vRhaTOpkeOS7n4lAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc50c303690edfc1a42ddd72a28db277d992715ca9e33e8a4b4839bdfdecdb8e","last_reissued_at":"2026-07-04T23:58:14.941279Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:14.941279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Luca Daniel, Tsui-Wei Weng, Yuh-Shyang Wang","submitted_at":"2019-08-18T00:23:21Z","abstract_excerpt":"Deep neural networks are known to be fragile to small adversarial perturbations. This issue becomes more critical when a neural network is interconnected with a physical system in a closed loop. In this paper, we show how to combine recent works on neural network certification tools (which are mainly used in static settings such as image classification) with robust control theory to certify a neural network policy in a control loop. Specifically, we give a sufficient condition and an algorithm to ensure that the closed loop state and control constraints are satisfied when the persistent advers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06353","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.06353/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":"1908.06353","created_at":"2026-07-04T23:58:14.941332+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06353v1","created_at":"2026-07-04T23:58:14.941332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06353","created_at":"2026-07-04T23:58:14.941332+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RIMGA3JB3P4","created_at":"2026-07-04T23:58:14.941332+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RIMGA3JB3P4DJBN","created_at":"2026-07-04T23:58:14.941332+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RIMGA3J","created_at":"2026-07-04T23:58:14.941332+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/3RIMGA3JB3P4DJBN3VZKFDNSO7","json":"https://pith.science/pith/3RIMGA3JB3P4DJBN3VZKFDNSO7.json","graph_json":"https://pith.science/api/pith-number/3RIMGA3JB3P4DJBN3VZKFDNSO7/graph.json","events_json":"https://pith.science/api/pith-number/3RIMGA3JB3P4DJBN3VZKFDNSO7/events.json","paper":"https://pith.science/paper/3RIMGA3J"},"agent_actions":{"view_html":"https://pith.science/pith/3RIMGA3JB3P4DJBN3VZKFDNSO7","download_json":"https://pith.science/pith/3RIMGA3JB3P4DJBN3VZKFDNSO7.json","view_paper":"https://pith.science/paper/3RIMGA3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06353&json=true","fetch_graph":"https://pith.science/api/pith-number/3RIMGA3JB3P4DJBN3VZKFDNSO7/graph.json","fetch_events":"https://pith.science/api/pith-number/3RIMGA3JB3P4DJBN3VZKFDNSO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RIMGA3JB3P4DJBN3VZKFDNSO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RIMGA3JB3P4DJBN3VZKFDNSO7/action/storage_attestation","attest_author":"https://pith.science/pith/3RIMGA3JB3P4DJBN3VZKFDNSO7/action/author_attestation","sign_citation":"https://pith.science/pith/3RIMGA3JB3P4DJBN3VZKFDNSO7/action/citation_signature","submit_replication":"https://pith.science/pith/3RIMGA3JB3P4DJBN3VZKFDNSO7/action/replication_record"}},"created_at":"2026-07-04T23:58:14.941332+00:00","updated_at":"2026-07-04T23:58:14.941332+00:00"}