{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PRUOWHECJ57TPJOQ5AB25CMDC7","short_pith_number":"pith:PRUOWHEC","schema_version":"1.0","canonical_sha256":"7c68eb1c824f7f37a5d0e803ae898317e50c0e36d695a91cc7cc5b72cc6d0e6e","source":{"kind":"arxiv","id":"2309.04798","version":1},"attestation_state":"computed","paper":{"title":"Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jia Zhang, Ke Xu, Kun Sun, Qilei Yin, Qi Li, Xinhao Deng, Yihao Chen, Yuqi Qing, Zhuotao Liu","submitted_at":"2023-09-09T13:49:30Z","abstract_excerpt":"Machine learning (ML) is promising in accurately detecting malicious flows in encrypted network traffic; however, it is challenging to collect a training dataset that contains a sufficient amount of encrypted malicious data with correct labels. When ML models are trained with low-quality training data, they suffer degraded performance. In this paper, we aim at addressing a real-world low-quality training dataset problem, namely, detecting encrypted malicious traffic generated by continuously evolving malware. We develop RAPIER that fully utilizes different distributions of normal and malicious"},"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":"2309.04798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-09-09T13:49:30Z","cross_cats_sorted":[],"title_canon_sha256":"156edd2adec7f3fba6f8c9fd9debd1bb54e526d589981be2ba02a864d8f72ffc","abstract_canon_sha256":"670744a8efc873732321e27918a448071545a4e465b4be66a318d8862a5788b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:27.273054Z","signature_b64":"KPXvwZ51uNm9l0JDY+yJJuxWesd5W53tK+/iUWVJ+iH27Q/OBedCfNaFguDXK2Mpx3mdL2N5Tap57kZ94q8KBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c68eb1c824f7f37a5d0e803ae898317e50c0e36d695a91cc7cc5b72cc6d0e6e","last_reissued_at":"2026-07-05T06:49:27.272539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:27.272539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jia Zhang, Ke Xu, Kun Sun, Qilei Yin, Qi Li, Xinhao Deng, Yihao Chen, Yuqi Qing, Zhuotao Liu","submitted_at":"2023-09-09T13:49:30Z","abstract_excerpt":"Machine learning (ML) is promising in accurately detecting malicious flows in encrypted network traffic; however, it is challenging to collect a training dataset that contains a sufficient amount of encrypted malicious data with correct labels. When ML models are trained with low-quality training data, they suffer degraded performance. In this paper, we aim at addressing a real-world low-quality training dataset problem, namely, detecting encrypted malicious traffic generated by continuously evolving malware. We develop RAPIER that fully utilizes different distributions of normal and malicious"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04798","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.04798/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":"2309.04798","created_at":"2026-07-05T06:49:27.272614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04798v1","created_at":"2026-07-05T06:49:27.272614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04798","created_at":"2026-07-05T06:49:27.272614+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRUOWHECJ57T","created_at":"2026-07-05T06:49:27.272614+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRUOWHECJ57TPJOQ","created_at":"2026-07-05T06:49:27.272614+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRUOWHEC","created_at":"2026-07-05T06:49:27.272614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13107","citing_title":"The Invisible Ink of the Android Malware World: A Longitudinal Study on the Usage of Covert Communication Channels","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7","json":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7.json","graph_json":"https://pith.science/api/pith-number/PRUOWHECJ57TPJOQ5AB25CMDC7/graph.json","events_json":"https://pith.science/api/pith-number/PRUOWHECJ57TPJOQ5AB25CMDC7/events.json","paper":"https://pith.science/paper/PRUOWHEC"},"agent_actions":{"view_html":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7","download_json":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7.json","view_paper":"https://pith.science/paper/PRUOWHEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04798&json=true","fetch_graph":"https://pith.science/api/pith-number/PRUOWHECJ57TPJOQ5AB25CMDC7/graph.json","fetch_events":"https://pith.science/api/pith-number/PRUOWHECJ57TPJOQ5AB25CMDC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7/action/storage_attestation","attest_author":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7/action/author_attestation","sign_citation":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7/action/citation_signature","submit_replication":"https://pith.science/pith/PRUOWHECJ57TPJOQ5AB25CMDC7/action/replication_record"}},"created_at":"2026-07-05T06:49:27.272614+00:00","updated_at":"2026-07-05T06:49:27.272614+00:00"}