{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SYWIQ2NFYHWZ2EN6T3MKKLQBRW","short_pith_number":"pith:SYWIQ2NF","schema_version":"1.0","canonical_sha256":"962c8869a5c1ed9d11be9ed8a52e018d859c4b74a4e242048eaf499314040564","source":{"kind":"arxiv","id":"2306.09318","version":1},"attestation_state":"computed","paper":{"title":"Inroads into Autonomous Network Defence using Explained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chris Hicks, Mia Wang, Myles Foley, Vasilios Mavroudis, Zoe M","submitted_at":"2023-06-15T17:53:14Z","abstract_excerpt":"Computer network defence is a complicated task that has necessitated a high degree of human involvement. However, with recent advancements in machine learning, fully autonomous network defence is becoming increasingly plausible. This paper introduces an end-to-end methodology for studying attack strategies, designing defence agents and explaining their operation. First, using state diagrams, we visualise adversarial behaviour to gain insight about potential points of intervention and inform the design of our defensive models. We opt to use a set of deep reinforcement learning agents trained on"},"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":"2306.09318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-06-15T17:53:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e689e6df46d77adfc5f717f217d925bec584745a777b4bb6a77da6dc23448f73","abstract_canon_sha256":"e2d4c7255cd9da19595a504dbb05e9c94124ed034468fe80c7c38f1acac556d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:10.892701Z","signature_b64":"anc6/4cZwCtUvL6uyfsagx65B5RgAkews9DJhDMkd5/XOkIMC1XwYG7wWHPUzTweOa8v8jUYZo4dK/U0t9x6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"962c8869a5c1ed9d11be9ed8a52e018d859c4b74a4e242048eaf499314040564","last_reissued_at":"2026-07-05T06:21:10.892274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:10.892274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inroads into Autonomous Network Defence using Explained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chris Hicks, Mia Wang, Myles Foley, Vasilios Mavroudis, Zoe M","submitted_at":"2023-06-15T17:53:14Z","abstract_excerpt":"Computer network defence is a complicated task that has necessitated a high degree of human involvement. However, with recent advancements in machine learning, fully autonomous network defence is becoming increasingly plausible. This paper introduces an end-to-end methodology for studying attack strategies, designing defence agents and explaining their operation. First, using state diagrams, we visualise adversarial behaviour to gain insight about potential points of intervention and inform the design of our defensive models. We opt to use a set of deep reinforcement learning agents trained on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09318","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/2306.09318/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":"2306.09318","created_at":"2026-07-05T06:21:10.892342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09318v1","created_at":"2026-07-05T06:21:10.892342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09318","created_at":"2026-07-05T06:21:10.892342+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYWIQ2NFYHWZ","created_at":"2026-07-05T06:21:10.892342+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYWIQ2NFYHWZ2EN6","created_at":"2026-07-05T06:21:10.892342+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYWIQ2NF","created_at":"2026-07-05T06:21:10.892342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.11708","citing_title":"Unveiling the Black Box: A Multi-Layer Framework for Explaining Reinforcement Learning-Based Cyber Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15163","citing_title":"Adaptive Network Security Policies via Belief Aggregation and Rollout","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW","json":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW.json","graph_json":"https://pith.science/api/pith-number/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/graph.json","events_json":"https://pith.science/api/pith-number/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/events.json","paper":"https://pith.science/paper/SYWIQ2NF"},"agent_actions":{"view_html":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW","download_json":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW.json","view_paper":"https://pith.science/paper/SYWIQ2NF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09318&json=true","fetch_graph":"https://pith.science/api/pith-number/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/graph.json","fetch_events":"https://pith.science/api/pith-number/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/action/storage_attestation","attest_author":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/action/author_attestation","sign_citation":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/action/citation_signature","submit_replication":"https://pith.science/pith/SYWIQ2NFYHWZ2EN6T3MKKLQBRW/action/replication_record"}},"created_at":"2026-07-05T06:21:10.892342+00:00","updated_at":"2026-07-05T06:21:10.892342+00:00"}