{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6LMTF3KSZ7BWIWIUBVPEBN4K4A","short_pith_number":"pith:6LMTF3KS","schema_version":"1.0","canonical_sha256":"f2d932ed52cfc36459140d5e40b78ae00d803139c37c326e4cdd28bce45cf54d","source":{"kind":"arxiv","id":"2407.08838","version":2},"attestation_state":"computed","paper":{"title":"Deep Learning for Network Anomaly Detection under Data Contamination: Evaluating Robustness and Mitigating Performance Degradation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.NI"],"primary_cat":"cs.LG","authors_text":"Arian Soltani, D'Jeff K. Nkashama, Froduald Kabanza, Jean-Charles Verdier, Jordan Masakuna F\\'elicien, Marc Frappier, Pierre-Martin Tardif","submitted_at":"2024-07-11T19:47:37Z","abstract_excerpt":"Deep learning (DL) has emerged as a crucial tool in network anomaly detection (NAD) for cybersecurity. While DL models for anomaly detection excel at extracting features and learning patterns from data, they are vulnerable to data contamination -- the inadvertent inclusion of attack-related data in training sets presumed benign. This study evaluates the robustness of six unsupervised DL algorithms against data contamination using our proposed evaluation protocol. Results demonstrate significant performance degradation in state-of-the-art anomaly detection algorithms when exposed to contaminate"},"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":"2407.08838","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-11T19:47:37Z","cross_cats_sorted":["cs.CR","cs.NI"],"title_canon_sha256":"9cc3e4e81a016ba920c114e0e7423ae9e24c44a14449ed91c07d19614ea0b8f1","abstract_canon_sha256":"8c10249f40a76108c1ba0d50b22b53a36565e3f29dd98b87754083bd3680eed4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:27.564821Z","signature_b64":"FTpLs6UgRk/kJsMTFkQDq78zRY5xi1R5cs+5mZo7/aQaGetcytIag5TPvidF5ETyoNMdvLzoorVYzPKEc/tZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2d932ed52cfc36459140d5e40b78ae00d803139c37c326e4cdd28bce45cf54d","last_reissued_at":"2026-07-05T09:06:27.564264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:27.564264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning for Network Anomaly Detection under Data Contamination: Evaluating Robustness and Mitigating Performance Degradation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.NI"],"primary_cat":"cs.LG","authors_text":"Arian Soltani, D'Jeff K. Nkashama, Froduald Kabanza, Jean-Charles Verdier, Jordan Masakuna F\\'elicien, Marc Frappier, Pierre-Martin Tardif","submitted_at":"2024-07-11T19:47:37Z","abstract_excerpt":"Deep learning (DL) has emerged as a crucial tool in network anomaly detection (NAD) for cybersecurity. While DL models for anomaly detection excel at extracting features and learning patterns from data, they are vulnerable to data contamination -- the inadvertent inclusion of attack-related data in training sets presumed benign. This study evaluates the robustness of six unsupervised DL algorithms against data contamination using our proposed evaluation protocol. Results demonstrate significant performance degradation in state-of-the-art anomaly detection algorithms when exposed to contaminate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08838","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/2407.08838/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":"2407.08838","created_at":"2026-07-05T09:06:27.564335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08838v2","created_at":"2026-07-05T09:06:27.564335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08838","created_at":"2026-07-05T09:06:27.564335+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LMTF3KSZ7BW","created_at":"2026-07-05T09:06:27.564335+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LMTF3KSZ7BWIWIU","created_at":"2026-07-05T09:06:27.564335+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LMTF3KS","created_at":"2026-07-05T09:06:27.564335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06550","citing_title":"Contrastive Self-Supervised Network Intrusion Detection using Augmented Negative Pairs","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A","json":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A.json","graph_json":"https://pith.science/api/pith-number/6LMTF3KSZ7BWIWIUBVPEBN4K4A/graph.json","events_json":"https://pith.science/api/pith-number/6LMTF3KSZ7BWIWIUBVPEBN4K4A/events.json","paper":"https://pith.science/paper/6LMTF3KS"},"agent_actions":{"view_html":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A","download_json":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A.json","view_paper":"https://pith.science/paper/6LMTF3KS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08838&json=true","fetch_graph":"https://pith.science/api/pith-number/6LMTF3KSZ7BWIWIUBVPEBN4K4A/graph.json","fetch_events":"https://pith.science/api/pith-number/6LMTF3KSZ7BWIWIUBVPEBN4K4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A/action/storage_attestation","attest_author":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A/action/author_attestation","sign_citation":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A/action/citation_signature","submit_replication":"https://pith.science/pith/6LMTF3KSZ7BWIWIUBVPEBN4K4A/action/replication_record"}},"created_at":"2026-07-05T09:06:27.564335+00:00","updated_at":"2026-07-05T09:06:27.564335+00:00"}