{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FEUH67AYBOQ2IHFMYSTLQJFXMS","short_pith_number":"pith:FEUH67AY","schema_version":"1.0","canonical_sha256":"29287f7c180ba1a41cacc4a6b824b764928ac7778f64d6ba32e2de5fa89af644","source":{"kind":"arxiv","id":"1811.00121","version":1},"attestation_state":"computed","paper":{"title":"A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"David J. Miller, George Kesidis, Xinyi Hu, Zhen Xiang","submitted_at":"2018-10-31T21:04:43Z","abstract_excerpt":"Naive Bayes spam filters are highly susceptible to data poisoning attacks. Here, known spam sources/blacklisted IPs exploit the fact that their received emails will be treated as (ground truth) labeled spam examples, and used for classifier training (or re-training). The attacking source thus generates emails that will skew the spam model, potentially resulting in great degradation in classifier accuracy. Such attacks are successful mainly because of the poor representation power of the naive Bayes (NB) model, with only a single (component) density to represent spam (plus a possible attack). W"},"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":"1811.00121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-10-31T21:04:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"fb1445bd2a1d1132306c1e08562177c0dd208d2191fd63f0e9d96c681ae0e95f","abstract_canon_sha256":"3640d154376b1351e68cca4263764de5342f917bfdc9694b76e200e8e5626bd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.200412Z","signature_b64":"YlM8rOrX35nnQWWy6tM4q5PicLDiFk99iQAvhsDtQVuh4SMuPj2fBS2yViWYv7RHV+KgF5CkzFNXmlQgj8zXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29287f7c180ba1a41cacc4a6b824b764928ac7778f64d6ba32e2de5fa89af644","last_reissued_at":"2026-05-18T00:01:48.199810Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.199810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"David J. Miller, George Kesidis, Xinyi Hu, Zhen Xiang","submitted_at":"2018-10-31T21:04:43Z","abstract_excerpt":"Naive Bayes spam filters are highly susceptible to data poisoning attacks. Here, known spam sources/blacklisted IPs exploit the fact that their received emails will be treated as (ground truth) labeled spam examples, and used for classifier training (or re-training). The attacking source thus generates emails that will skew the spam model, potentially resulting in great degradation in classifier accuracy. Such attacks are successful mainly because of the poor representation power of the naive Bayes (NB) model, with only a single (component) density to represent spam (plus a possible attack). W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00121","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":"1811.00121","created_at":"2026-05-18T00:01:48.199901+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00121v1","created_at":"2026-05-18T00:01:48.199901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00121","created_at":"2026-05-18T00:01:48.199901+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEUH67AYBOQ2","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEUH67AYBOQ2IHFM","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEUH67AY","created_at":"2026-05-18T12:32:22.470017+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/FEUH67AYBOQ2IHFMYSTLQJFXMS","json":"https://pith.science/pith/FEUH67AYBOQ2IHFMYSTLQJFXMS.json","graph_json":"https://pith.science/api/pith-number/FEUH67AYBOQ2IHFMYSTLQJFXMS/graph.json","events_json":"https://pith.science/api/pith-number/FEUH67AYBOQ2IHFMYSTLQJFXMS/events.json","paper":"https://pith.science/paper/FEUH67AY"},"agent_actions":{"view_html":"https://pith.science/pith/FEUH67AYBOQ2IHFMYSTLQJFXMS","download_json":"https://pith.science/pith/FEUH67AYBOQ2IHFMYSTLQJFXMS.json","view_paper":"https://pith.science/paper/FEUH67AY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00121&json=true","fetch_graph":"https://pith.science/api/pith-number/FEUH67AYBOQ2IHFMYSTLQJFXMS/graph.json","fetch_events":"https://pith.science/api/pith-number/FEUH67AYBOQ2IHFMYSTLQJFXMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEUH67AYBOQ2IHFMYSTLQJFXMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEUH67AYBOQ2IHFMYSTLQJFXMS/action/storage_attestation","attest_author":"https://pith.science/pith/FEUH67AYBOQ2IHFMYSTLQJFXMS/action/author_attestation","sign_citation":"https://pith.science/pith/FEUH67AYBOQ2IHFMYSTLQJFXMS/action/citation_signature","submit_replication":"https://pith.science/pith/FEUH67AYBOQ2IHFMYSTLQJFXMS/action/replication_record"}},"created_at":"2026-05-18T00:01:48.199901+00:00","updated_at":"2026-05-18T00:01:48.199901+00:00"}