{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Y5R72PA5ZIRT2BPH3WMTQ6HUY7","short_pith_number":"pith:Y5R72PA5","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"},"canonical_sha256":"c763fd3c1dca233d05e7dd993878f4c7c372d19a23c3f1a6b7d4d72013aa7684","source":{"kind":"arxiv","id":"1808.05770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.05770","created_at":"2026-05-18T00:07:52Z"},{"alias_kind":"arxiv_version","alias_value":"1808.05770v1","created_at":"2026-05-18T00:07:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05770","created_at":"2026-05-18T00:07:52Z"},{"alias_kind":"pith_short_12","alias_value":"Y5R72PA5ZIRT","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y5R72PA5ZIRT2BPH","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y5R72PA5","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Y5R72PA5ZIRT2BPH3WMTQ6HUY7","target":"record","payload":{"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"},"canonical_sha256":"c763fd3c1dca233d05e7dd993878f4c7c372d19a23c3f1a6b7d4d72013aa7684","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"},"source_kind":"arxiv","source_id":"1808.05770","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZCuib7fNM+gtW+hZmEVwNTWf9ffusZQqwr9kkEHmyPhAaEPrKwQzdhjKmIzY+C8eZtelgq0EZce6hf084rUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T13:32:43.034705Z"},"content_sha256":"7953e26418280b628b57ee3d316df26570aca7d0db4fbdae6fe1d10afba3c16e","schema_version":"1.0","event_id":"sha256:7953e26418280b628b57ee3d316df26570aca7d0db4fbdae6fe1d10afba3c16e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Y5R72PA5ZIRT2BPH3WMTQ6HUY7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wzlfBI9L7QGJHXaA1xZj5IaBn6KuY5IjixBXLmhZH2dLHSO1YDtPeyOrekcOonXfttsk6YsQEhS5YSFkLv/mCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T13:32:43.035057Z"},"content_sha256":"b3fad92fe6615485dc4118ec6272e66518997649662d749982ad0ea7c0817de8","schema_version":"1.0","event_id":"sha256:b3fad92fe6615485dc4118ec6272e66518997649662d749982ad0ea7c0817de8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/bundle.json","state_url":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T13:32:43Z","links":{"resolver":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7","bundle":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/bundle.json","state":"https://pith.science/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5R72PA5ZIRT2BPH3WMTQ6HUY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y5R72PA5ZIRT2BPH3WMTQ6HUY7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"63b3ed55761ae8338c812207c077cb432d0f7dca72d85b58f05603beb596975f","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-08-17T06:34:53Z","title_canon_sha256":"38280d38f339a26aae1063089daa22e28038eb6138b0df915f92e6cabdc789e6"},"schema_version":"1.0","source":{"id":"1808.05770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.05770","created_at":"2026-05-18T00:07:52Z"},{"alias_kind":"arxiv_version","alias_value":"1808.05770v1","created_at":"2026-05-18T00:07:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05770","created_at":"2026-05-18T00:07:52Z"},{"alias_kind":"pith_short_12","alias_value":"Y5R72PA5ZIRT","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y5R72PA5ZIRT2BPH","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y5R72PA5","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:b3fad92fe6615485dc4118ec6272e66518997649662d749982ad0ea7c0817de8","target":"graph","created_at":"2026-05-18T00:07:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Benjamin I.P. Rubinstein, Christopher Leckie, David Hubczenko, Olivier De Vel, Paul Montague, Sarah Erfani, Tamas Abraham, Tansu Alpcan, Yi Han","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-08-17T06:34:53Z","title":"Reinforcement Learning for Autonomous Defence in Software-Defined Networking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05770","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7953e26418280b628b57ee3d316df26570aca7d0db4fbdae6fe1d10afba3c16e","target":"record","created_at":"2026-05-18T00:07:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"63b3ed55761ae8338c812207c077cb432d0f7dca72d85b58f05603beb596975f","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-08-17T06:34:53Z","title_canon_sha256":"38280d38f339a26aae1063089daa22e28038eb6138b0df915f92e6cabdc789e6"},"schema_version":"1.0","source":{"id":"1808.05770","kind":"arxiv","version":1}},"canonical_sha256":"c763fd3c1dca233d05e7dd993878f4c7c372d19a23c3f1a6b7d4d72013aa7684","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c763fd3c1dca233d05e7dd993878f4c7c372d19a23c3f1a6b7d4d72013aa7684","first_computed_at":"2026-05-18T00:07:52.204580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:52.204580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w4cZl9t1EWyvmfzvk9dP3wCakft/NuWqg6+YC2GsyZvgkhBw6iFb7qa4oBpjj9eyUfQG4nAHrWgtDSBwc7vGCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:52.205200Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.05770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7953e26418280b628b57ee3d316df26570aca7d0db4fbdae6fe1d10afba3c16e","sha256:b3fad92fe6615485dc4118ec6272e66518997649662d749982ad0ea7c0817de8"],"state_sha256":"76f39b120040a5e9093793d8dcb913764cd829b52d42be8669e716ccc290cc3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Om/uUExhSgxQdPfiWcbF+g05f2MXBwN4EhBl5sEQgOceR5vlJTzwL24s62MpgHWulNeyA7MFVl38/i3Rj6J7Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T13:32:43.037084Z","bundle_sha256":"9c06bb8c651cab8b0f2103e9f56cdb4363298c2ed66783af9c7a574dd5701d62"}}