{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Y6SBUB4ARMHTHGQFAJI3VOTBCW","short_pith_number":"pith:Y6SBUB4A","schema_version":"1.0","canonical_sha256":"c7a41a07808b0f339a050251baba6115bc2c486e25ddd632a8c522648887376d","source":{"kind":"arxiv","id":"1604.08275","version":1},"attestation_state":"computed","paper":{"title":"Crafting Adversarial Input Sequences for Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CR","authors_text":"Ananthram Swami, Nicolas Papernot, Patrick McDaniel, Richard Harang","submitted_at":"2016-04-28T00:35:32Z","abstract_excerpt":"Machine learning models are frequently used to solve complex security problems, as well as to make decisions in sensitive situations like guiding autonomous vehicles or predicting financial market behaviors. Previous efforts have shown that numerous machine learning models were vulnerable to adversarial manipulations of their inputs taking the form of adversarial samples. Such inputs are crafted by adding carefully selected perturbations to legitimate inputs so as to force the machine learning model to misbehave, for instance by outputting a wrong class if the machine learning task of interest"},"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":"1604.08275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2016-04-28T00:35:32Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"690c71f7c77e0e9201e2d26b1b576a29b4526a1d00775d55428ae45bbf0a7bd6","abstract_canon_sha256":"17c903838d37ef3c8e7bb25bc686990f3338fe7f4a96534fb8e22882cfa1741f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:04.403946Z","signature_b64":"0PKaB9bXuTbcWf8Lt+UfPr7RxcM2VSzBDc/4ITP+QApn6kcBMuSLf7XgySiE+QeAosydo1j2bmu+lceo+VILAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7a41a07808b0f339a050251baba6115bc2c486e25ddd632a8c522648887376d","last_reissued_at":"2026-05-18T01:16:04.403251Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:04.403251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crafting Adversarial Input Sequences for Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CR","authors_text":"Ananthram Swami, Nicolas Papernot, Patrick McDaniel, Richard Harang","submitted_at":"2016-04-28T00:35:32Z","abstract_excerpt":"Machine learning models are frequently used to solve complex security problems, as well as to make decisions in sensitive situations like guiding autonomous vehicles or predicting financial market behaviors. Previous efforts have shown that numerous machine learning models were vulnerable to adversarial manipulations of their inputs taking the form of adversarial samples. Such inputs are crafted by adding carefully selected perturbations to legitimate inputs so as to force the machine learning model to misbehave, for instance by outputting a wrong class if the machine learning task of interest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.08275","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":"1604.08275","created_at":"2026-05-18T01:16:04.403383+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.08275v1","created_at":"2026-05-18T01:16:04.403383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.08275","created_at":"2026-05-18T01:16:04.403383+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6SBUB4ARMHT","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6SBUB4ARMHTHGQF","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6SBUB4A","created_at":"2026-05-18T12:30:53.716459+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/Y6SBUB4ARMHTHGQFAJI3VOTBCW","json":"https://pith.science/pith/Y6SBUB4ARMHTHGQFAJI3VOTBCW.json","graph_json":"https://pith.science/api/pith-number/Y6SBUB4ARMHTHGQFAJI3VOTBCW/graph.json","events_json":"https://pith.science/api/pith-number/Y6SBUB4ARMHTHGQFAJI3VOTBCW/events.json","paper":"https://pith.science/paper/Y6SBUB4A"},"agent_actions":{"view_html":"https://pith.science/pith/Y6SBUB4ARMHTHGQFAJI3VOTBCW","download_json":"https://pith.science/pith/Y6SBUB4ARMHTHGQFAJI3VOTBCW.json","view_paper":"https://pith.science/paper/Y6SBUB4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.08275&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6SBUB4ARMHTHGQFAJI3VOTBCW/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6SBUB4ARMHTHGQFAJI3VOTBCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6SBUB4ARMHTHGQFAJI3VOTBCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6SBUB4ARMHTHGQFAJI3VOTBCW/action/storage_attestation","attest_author":"https://pith.science/pith/Y6SBUB4ARMHTHGQFAJI3VOTBCW/action/author_attestation","sign_citation":"https://pith.science/pith/Y6SBUB4ARMHTHGQFAJI3VOTBCW/action/citation_signature","submit_replication":"https://pith.science/pith/Y6SBUB4ARMHTHGQFAJI3VOTBCW/action/replication_record"}},"created_at":"2026-05-18T01:16:04.403383+00:00","updated_at":"2026-05-18T01:16:04.403383+00:00"}