{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KCMVU3UENJVRQ7UHLOOUIVMEQQ","short_pith_number":"pith:KCMVU3UE","schema_version":"1.0","canonical_sha256":"50995a6e846a6b187e875b9d44558484211d0aafe234da1c6f0bf628ea425a8f","source":{"kind":"arxiv","id":"2002.05646","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Machine Learning -- Industry Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ML"],"primary_cat":"cs.CY","authors_text":"Andi Comissoneru, Andrew Marshall, John Lambert, Magnus Nystr\\\"om, Mario Goertzel, Matt Swann, Ram Shankar Siva Kumar, Sharon Xia","submitted_at":"2020-02-04T02:28:34Z","abstract_excerpt":"Based on interviews with 28 organizations, we found that industry practitioners are not equipped with tactical and strategic tools to protect, detect and respond to attacks on their Machine Learning (ML) systems. We leverage the insights from the interviews and we enumerate the gaps in perspective in securing machine learning systems when viewed in the context of traditional software security development. We write this paper from the perspective of two personas: developers/ML engineers and security incident responders who are tasked with securing ML systems as they are designed, developed and "},"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":"2002.05646","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2020-02-04T02:28:34Z","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"title_canon_sha256":"3c68f2f120d1a001656bea243163a2ebb60cf73f45d785cfc4dcf37e2f16939c","abstract_canon_sha256":"a475347e270e26e4e5707e97c1be7207f38a3f1aacf772d827d995d25cbbdeb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:28.469624Z","signature_b64":"MN47jQnsoQ7veKDL1dgCKfx8XJQV7ZbS5pHG3b0nZq065dvIgcgSboSaMoRHv2ws3NgsltrYtX6yoZzEewlyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50995a6e846a6b187e875b9d44558484211d0aafe234da1c6f0bf628ea425a8f","last_reissued_at":"2026-07-05T02:24:28.469260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:28.469260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Machine Learning -- Industry Perspectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ML"],"primary_cat":"cs.CY","authors_text":"Andi Comissoneru, Andrew Marshall, John Lambert, Magnus Nystr\\\"om, Mario Goertzel, Matt Swann, Ram Shankar Siva Kumar, Sharon Xia","submitted_at":"2020-02-04T02:28:34Z","abstract_excerpt":"Based on interviews with 28 organizations, we found that industry practitioners are not equipped with tactical and strategic tools to protect, detect and respond to attacks on their Machine Learning (ML) systems. We leverage the insights from the interviews and we enumerate the gaps in perspective in securing machine learning systems when viewed in the context of traditional software security development. We write this paper from the perspective of two personas: developers/ML engineers and security incident responders who are tasked with securing ML systems as they are designed, developed and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05646","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.05646/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":"2002.05646","created_at":"2026-07-05T02:24:28.469321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05646v3","created_at":"2026-07-05T02:24:28.469321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05646","created_at":"2026-07-05T02:24:28.469321+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCMVU3UENJVR","created_at":"2026-07-05T02:24:28.469321+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCMVU3UENJVRQ7UH","created_at":"2026-07-05T02:24:28.469321+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCMVU3UE","created_at":"2026-07-05T02:24:28.469321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17300","citing_title":"The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributes","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ","json":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ.json","graph_json":"https://pith.science/api/pith-number/KCMVU3UENJVRQ7UHLOOUIVMEQQ/graph.json","events_json":"https://pith.science/api/pith-number/KCMVU3UENJVRQ7UHLOOUIVMEQQ/events.json","paper":"https://pith.science/paper/KCMVU3UE"},"agent_actions":{"view_html":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ","download_json":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ.json","view_paper":"https://pith.science/paper/KCMVU3UE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05646&json=true","fetch_graph":"https://pith.science/api/pith-number/KCMVU3UENJVRQ7UHLOOUIVMEQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KCMVU3UENJVRQ7UHLOOUIVMEQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ/action/storage_attestation","attest_author":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ/action/author_attestation","sign_citation":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ/action/citation_signature","submit_replication":"https://pith.science/pith/KCMVU3UENJVRQ7UHLOOUIVMEQQ/action/replication_record"}},"created_at":"2026-07-05T02:24:28.469321+00:00","updated_at":"2026-07-05T02:24:28.469321+00:00"}