{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RRKCYTJAH6ZL6AMAKRTPMWL65X","short_pith_number":"pith:RRKCYTJA","schema_version":"1.0","canonical_sha256":"8c542c4d203fb2bf01805466f6597eedf9c58dc4eb093a3d17758ecf2ae3912a","source":{"kind":"arxiv","id":"1906.07773","version":2},"attestation_state":"computed","paper":{"title":"Poisoning Attacks with Generative Adversarial Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bjarne Pfitzner, Emil C. Lupu, Javier Carnerero-Cano, Luis Mu\\~noz-Gonz\\'alez, Matteo Russo","submitted_at":"2019-06-18T19:14:09Z","abstract_excerpt":"Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-level optimization problem. Solving these problems is computationally demanding and has limited applicability for some models such as deep networks. In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers genera"},"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":"1906.07773","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-18T19:14:09Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"fe666cfe1bfed7bd1d6c9091bdfc2a27b34c7b21b59e78e549959e73813c6108","abstract_canon_sha256":"3117671bffdcbbf378c43fb2f8efe6324172c564fb72a5d6b2ea67b0740119e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:17.411717Z","signature_b64":"snms129E0V3nRBdVv8nrUm2/7Q+K6x7g3SmMTHVnNtxlaqAv4klNkFBK+Y6g5mbejvRirfszSd20hoDtHkkzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c542c4d203fb2bf01805466f6597eedf9c58dc4eb093a3d17758ecf2ae3912a","last_reissued_at":"2026-07-05T00:07:17.411114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:17.411114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Poisoning Attacks with Generative Adversarial Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bjarne Pfitzner, Emil C. Lupu, Javier Carnerero-Cano, Luis Mu\\~noz-Gonz\\'alez, Matteo Russo","submitted_at":"2019-06-18T19:14:09Z","abstract_excerpt":"Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-level optimization problem. Solving these problems is computationally demanding and has limited applicability for some models such as deep networks. In this paper we introduce a novel generative model to craft systematic poisoning attacks against machine learning classifiers genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07773","kind":"arxiv","version":2},"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/1906.07773/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":"1906.07773","created_at":"2026-07-05T00:07:17.411171+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07773v2","created_at":"2026-07-05T00:07:17.411171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07773","created_at":"2026-07-05T00:07:17.411171+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRKCYTJAH6ZL","created_at":"2026-07-05T00:07:17.411171+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRKCYTJAH6ZL6AMA","created_at":"2026-07-05T00:07:17.411171+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRKCYTJA","created_at":"2026-07-05T00:07:17.411171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05403","citing_title":"Poisoning Behavioral-based Worker Selection in Mobile Crowdsensing using Generative Adversarial Networks","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X","json":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X.json","graph_json":"https://pith.science/api/pith-number/RRKCYTJAH6ZL6AMAKRTPMWL65X/graph.json","events_json":"https://pith.science/api/pith-number/RRKCYTJAH6ZL6AMAKRTPMWL65X/events.json","paper":"https://pith.science/paper/RRKCYTJA"},"agent_actions":{"view_html":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X","download_json":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X.json","view_paper":"https://pith.science/paper/RRKCYTJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07773&json=true","fetch_graph":"https://pith.science/api/pith-number/RRKCYTJAH6ZL6AMAKRTPMWL65X/graph.json","fetch_events":"https://pith.science/api/pith-number/RRKCYTJAH6ZL6AMAKRTPMWL65X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X/action/storage_attestation","attest_author":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X/action/author_attestation","sign_citation":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X/action/citation_signature","submit_replication":"https://pith.science/pith/RRKCYTJAH6ZL6AMAKRTPMWL65X/action/replication_record"}},"created_at":"2026-07-05T00:07:17.411171+00:00","updated_at":"2026-07-05T00:07:17.411171+00:00"}