{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y5R72PA5ZIRT2BPH3WMTQ6HUY7","short_pith_number":"pith:Y5R72PA5","schema_version":"1.0","canonical_sha256":"c763fd3c1dca233d05e7dd993878f4c7c372d19a23c3f1a6b7d4d72013aa7684","source":{"kind":"arxiv","id":"1808.05770","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Autonomous Defence in Software-Defined Networking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Benjamin I.P. Rubinstein, Christopher Leckie, David Hubczenko, Olivier De Vel, Paul Montague, Sarah Erfani, Tamas Abraham, Tansu Alpcan, Yi Han","submitted_at":"2018-08-17T06:34:53Z","abstract_excerpt":"Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade classification. In this paper, we investigate the feasibility of applying a specific class of machine learning algorithms, namely, reinforcement learning (RL) algorithms, for autonomous cyber defence in software-defined networking (SDN). In particular, we focus on how an RL agent reacts towards different forms of causative attacks that poison its training process, includ"},"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":"1808.05770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-08-17T06:34:53Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"38280d38f339a26aae1063089daa22e28038eb6138b0df915f92e6cabdc789e6","abstract_canon_sha256":"63b3ed55761ae8338c812207c077cb432d0f7dca72d85b58f05603beb596975f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:52.205200Z","signature_b64":"w4cZl9t1EWyvmfzvk9dP3wCakft/NuWqg6+YC2GsyZvgkhBw6iFb7qa4oBpjj9eyUfQG4nAHrWgtDSBwc7vGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c763fd3c1dca233d05e7dd993878f4c7c372d19a23c3f1a6b7d4d72013aa7684","last_reissued_at":"2026-05-18T00:07:52.204580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:52.204580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Autonomous Defence in Software-Defined Networking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Benjamin I.P. Rubinstein, Christopher Leckie, David Hubczenko, Olivier De Vel, Paul Montague, Sarah Erfani, Tamas Abraham, Tansu Alpcan, Yi Han","submitted_at":"2018-08-17T06:34:53Z","abstract_excerpt":"Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade classification. In this paper, we investigate the feasibility of applying a specific class of machine learning algorithms, namely, reinforcement learning (RL) algorithms, for autonomous cyber defence in software-defined networking (SDN). In particular, we focus on how an RL agent reacts towards different forms of causative attacks that poison its training process, includ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05770","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":"1808.05770","created_at":"2026-05-18T00:07:52.204700+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.05770v1","created_at":"2026-05-18T00:07:52.204700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05770","created_at":"2026-05-18T00:07:52.204700+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5R72PA5ZIRT","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5R72PA5ZIRT2BPH","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5R72PA5","created_at":"2026-05-18T12:33:04.347982+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/Y5R72PA5ZIRT2BPH3WMTQ6HUY7","json":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7.json","graph_json":"https://pith.science/api/pith-number/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/graph.json","events_json":"https://pith.science/api/pith-number/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/events.json","paper":"https://pith.science/paper/Y5R72PA5"},"agent_actions":{"view_html":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7","download_json":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7.json","view_paper":"https://pith.science/paper/Y5R72PA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.05770&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/action/storage_attestation","attest_author":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/action/author_attestation","sign_citation":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/action/citation_signature","submit_replication":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/action/replication_record"}},"created_at":"2026-05-18T00:07:52.204700+00:00","updated_at":"2026-05-18T00:07:52.204700+00:00"}