{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XMSP6GVRJEJABJXC6RPQQVKDP3","short_pith_number":"pith:XMSP6GVR","schema_version":"1.0","canonical_sha256":"bb24ff1ab1491200a6e2f45f0855437eee31374742a315d0b0edb6b0eb373b9f","source":{"kind":"arxiv","id":"2603.17717","version":4},"attestation_state":"computed","paper":{"title":"Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A unified feature space from four reprocessed NIDS datasets supports stable machine learning classification of attacks and high-fidelity adversarial synthetic data generation.","cross_cats":["cs.AI","stat.AP","stat.ML"],"primary_cat":"cs.CR","authors_text":"Christos Douligeris, Iakovos-Christos Zarkadis","submitted_at":"2026-03-18T13:35:02Z","abstract_excerpt":"Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. In this paper, we address two tasks, in the first unified multi-modal NIDS dataset, which incorporates flow-level data, packet payload information and temporal "},"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":"2603.17717","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-03-18T13:35:02Z","cross_cats_sorted":["cs.AI","stat.AP","stat.ML"],"title_canon_sha256":"7dfb6f2135ca6cef92135b7ffe388dd052656bbb5ac04e0538f754d5ed954e6b","abstract_canon_sha256":"6dc2572979ca5d8b8a2d9b8018fb58f50c1c7bb69a1b49eea122a4937cb428b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:20:07.545258Z","signature_b64":"kMNl2AO3hVZTlxSHmGOJt7SU6OB1mumctx4HcSoQibbIZc+1/VzJRvf2OviUY+vkQ2xmk2GVjNTi2NuzQ+0bDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb24ff1ab1491200a6e2f45f0855437eee31374742a315d0b0edb6b0eb373b9f","last_reissued_at":"2026-07-13T01:20:07.543794Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:20:07.543794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A unified feature space from four reprocessed NIDS datasets supports stable machine learning classification of attacks and high-fidelity adversarial synthetic data generation.","cross_cats":["cs.AI","stat.AP","stat.ML"],"primary_cat":"cs.CR","authors_text":"Christos Douligeris, Iakovos-Christos Zarkadis","submitted_at":"2026-03-18T13:35:02Z","abstract_excerpt":"Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time for artificial intelligence (AI), with even more sophisticated attacks that utilize advanced techniques, such as generative artificial intelligence (GenAI) and reinforcement learning, it has become a vital component if we wish to protect our personal data, which are scattered across the web. In this paper, we address two tasks, in the first unified multi-modal NIDS dataset, which incorporates flow-level data, packet payload information and temporal "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The findings provide stable ML models for intrusion detection and generative models with high fidelity and utility, by combining the Synthetic Data Vault framework, the TRTS and TSTR tests, with non-parametric statistical tests and f-divergence measures.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That reprocessing the four source datasets into a single feature space preserves all critical attack signals and does not introduce systematic biases or information loss from the original collections.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A unified multi-modal NIDS dataset from CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019 is used to train stable ML attack classifiers and to generate synthetic data whose fidelity and utility are assessed via SDV, f-divergences, TRTS/TSTR tests and non-parametric statistics.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A unified feature space from four reprocessed NIDS datasets supports stable machine learning classification of attacks and high-fidelity adversarial synthetic data generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c17f2f5d8ce14885823ceb42659a732f33636991af58bf9b42e59b8cfad244aa"},"source":{"id":"2603.17717","kind":"arxiv","version":4},"verdict":{"id":"390a2ed1-7383-452d-b3ab-09cc53142f28","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T08:53:50.043582Z","strongest_claim":"The findings provide stable ML models for intrusion detection and generative models with high fidelity and utility, by combining the Synthetic Data Vault framework, the TRTS and TSTR tests, with non-parametric statistical tests and f-divergence measures.","one_line_summary":"A unified multi-modal NIDS dataset from CIC-IDS-2017, CIC-IoT-2023, UNSW-NB15 and CIC-DDoS-2019 is used to train stable ML attack classifiers and to generate synthetic data whose fidelity and utility are assessed via SDV, f-divergences, TRTS/TSTR tests and non-parametric statistics.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That reprocessing the four source datasets into a single feature space preserves all critical attack signals and does not introduce systematic biases or information loss from the original collections.","pith_extraction_headline":"A unified feature space from four reprocessed NIDS datasets supports stable machine learning classification of attacks and high-fidelity adversarial synthetic data generation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.17717/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":"2603.17717","created_at":"2026-07-13T01:20:07.544485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.17717v4","created_at":"2026-07-13T01:20:07.544485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.17717","created_at":"2026-07-13T01:20:07.544485+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMSP6GVRJEJA","created_at":"2026-07-13T01:20:07.544485+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMSP6GVRJEJABJXC","created_at":"2026-07-13T01:20:07.544485+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMSP6GVR","created_at":"2026-07-13T01:20:07.544485+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/XMSP6GVRJEJABJXC6RPQQVKDP3","json":"https://pith.science/pith/XMSP6GVRJEJABJXC6RPQQVKDP3.json","graph_json":"https://pith.science/api/pith-number/XMSP6GVRJEJABJXC6RPQQVKDP3/graph.json","events_json":"https://pith.science/api/pith-number/XMSP6GVRJEJABJXC6RPQQVKDP3/events.json","paper":"https://pith.science/paper/XMSP6GVR"},"agent_actions":{"view_html":"https://pith.science/pith/XMSP6GVRJEJABJXC6RPQQVKDP3","download_json":"https://pith.science/pith/XMSP6GVRJEJABJXC6RPQQVKDP3.json","view_paper":"https://pith.science/paper/XMSP6GVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.17717&json=true","fetch_graph":"https://pith.science/api/pith-number/XMSP6GVRJEJABJXC6RPQQVKDP3/graph.json","fetch_events":"https://pith.science/api/pith-number/XMSP6GVRJEJABJXC6RPQQVKDP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMSP6GVRJEJABJXC6RPQQVKDP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMSP6GVRJEJABJXC6RPQQVKDP3/action/storage_attestation","attest_author":"https://pith.science/pith/XMSP6GVRJEJABJXC6RPQQVKDP3/action/author_attestation","sign_citation":"https://pith.science/pith/XMSP6GVRJEJABJXC6RPQQVKDP3/action/citation_signature","submit_replication":"https://pith.science/pith/XMSP6GVRJEJABJXC6RPQQVKDP3/action/replication_record"}},"created_at":"2026-07-13T01:20:07.544485+00:00","updated_at":"2026-07-13T01:20:07.544485+00:00"}