{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EYBEPZXXL3LVPIBK4SCRPRIJVI","short_pith_number":"pith:EYBEPZXX","schema_version":"1.0","canonical_sha256":"260247e6f75ed757a02ae48517c509aa3a1fb815583f25bb2f4c96220cedd338","source":{"kind":"arxiv","id":"1906.02282","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Gradient-based Attacks with Symbolic Intervals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Abdou, Shiqi Wang, Suman Jana, Yizheng Chen","submitted_at":"2019-06-05T19:58:07Z","abstract_excerpt":"Recent breakthroughs in defenses against adversarial examples, like adversarial training, make the neural networks robust against various classes of attackers (e.g., first-order gradient-based attacks). However, it is an open question whether the adversarially trained networks are truly robust under unknown attacks. In this paper, we present interval attacks, a new technique to find adversarial examples to evaluate the robustness of neural networks. Interval attacks leverage symbolic interval propagation, a bound propagation technique that can exploit a broader view around the current input to"},"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":"1906.02282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T19:58:07Z","cross_cats_sorted":["cs.CR","cs.LO","stat.ML"],"title_canon_sha256":"8392431ec579bde3b1505d601ab15c6468d8e4753015078ee9f51e427de46402","abstract_canon_sha256":"86a3dcff9a18b9e5ed69f12445bf8b91af72492d44aaa9e7f5b631929696f04e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:01.698941Z","signature_b64":"sybMCnHbaqnEddZdRIZjZrcBLahiusydCZ3GQ6LBk8nnJyp8j/WWEUJl/wvegjj7uchKLyLv6P6CItIWb2JDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"260247e6f75ed757a02ae48517c509aa3a1fb815583f25bb2f4c96220cedd338","last_reissued_at":"2026-05-17T23:44:01.698432Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:01.698432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Gradient-based Attacks with Symbolic Intervals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Abdou, Shiqi Wang, Suman Jana, Yizheng Chen","submitted_at":"2019-06-05T19:58:07Z","abstract_excerpt":"Recent breakthroughs in defenses against adversarial examples, like adversarial training, make the neural networks robust against various classes of attackers (e.g., first-order gradient-based attacks). However, it is an open question whether the adversarially trained networks are truly robust under unknown attacks. In this paper, we present interval attacks, a new technique to find adversarial examples to evaluate the robustness of neural networks. Interval attacks leverage symbolic interval propagation, a bound propagation technique that can exploit a broader view around the current input to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02282","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":"1906.02282","created_at":"2026-05-17T23:44:01.698516+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02282v1","created_at":"2026-05-17T23:44:01.698516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02282","created_at":"2026-05-17T23:44:01.698516+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYBEPZXXL3LV","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYBEPZXXL3LVPIBK","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYBEPZXX","created_at":"2026-05-18T12:33:15.570797+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/EYBEPZXXL3LVPIBK4SCRPRIJVI","json":"https://pith.science/pith/EYBEPZXXL3LVPIBK4SCRPRIJVI.json","graph_json":"https://pith.science/api/pith-number/EYBEPZXXL3LVPIBK4SCRPRIJVI/graph.json","events_json":"https://pith.science/api/pith-number/EYBEPZXXL3LVPIBK4SCRPRIJVI/events.json","paper":"https://pith.science/paper/EYBEPZXX"},"agent_actions":{"view_html":"https://pith.science/pith/EYBEPZXXL3LVPIBK4SCRPRIJVI","download_json":"https://pith.science/pith/EYBEPZXXL3LVPIBK4SCRPRIJVI.json","view_paper":"https://pith.science/paper/EYBEPZXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02282&json=true","fetch_graph":"https://pith.science/api/pith-number/EYBEPZXXL3LVPIBK4SCRPRIJVI/graph.json","fetch_events":"https://pith.science/api/pith-number/EYBEPZXXL3LVPIBK4SCRPRIJVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYBEPZXXL3LVPIBK4SCRPRIJVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYBEPZXXL3LVPIBK4SCRPRIJVI/action/storage_attestation","attest_author":"https://pith.science/pith/EYBEPZXXL3LVPIBK4SCRPRIJVI/action/author_attestation","sign_citation":"https://pith.science/pith/EYBEPZXXL3LVPIBK4SCRPRIJVI/action/citation_signature","submit_replication":"https://pith.science/pith/EYBEPZXXL3LVPIBK4SCRPRIJVI/action/replication_record"}},"created_at":"2026-05-17T23:44:01.698516+00:00","updated_at":"2026-05-17T23:44:01.698516+00:00"}