{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JOROJ6QCGJ5JFB5LC2OARRLZNJ","short_pith_number":"pith:JOROJ6QC","schema_version":"1.0","canonical_sha256":"4ba2e4fa02327a9287ab169c08c5796a4c4e2e78e6523e69f296f643554fe38c","source":{"kind":"arxiv","id":"2407.15656","version":1},"attestation_state":"computed","paper":{"title":"Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Daniel Reti, Evridiki V. Ntagiou, Hans D. Schotten, Marcus Wallum, Norman Becker","submitted_at":"2024-07-22T14:17:29Z","abstract_excerpt":"Penetration testing is the process of searching for security weaknesses by simulating an attack. It is usually performed by experienced professionals, where scanning and attack tools are applied. By automating the execution of such tools, the need for human interaction and decision-making could be reduced. In this work, a Network Attack Simulator (NASim) was used as an environment to train reinforcement learning agents to solve three predefined security scenarios. These scenarios cover techniques of exploitation, post-exploitation and wiretapping. A large hyperparameter grid search was perform"},"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":"2407.15656","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-07-22T14:17:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d00a71c7039f8a9362ee5bb8b4c18c73255f4c3921cb5c2403e403c81944c1ce","abstract_canon_sha256":"ee60dc0ea08b3fb584af7b5c60550b7d4964221c66df69f390e7760369269c22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:59.387115Z","signature_b64":"of9HUscZfYcfz3tIvaRycrhdUGc8APbr53ahaDTGTud3GQlby07cX+ql8ibZ+FIx4Osnh0nQL6naRGcKPVtAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ba2e4fa02327a9287ab169c08c5796a4c4e2e78e6523e69f296f643554fe38c","last_reissued_at":"2026-07-05T08:46:59.386613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:59.386613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Reinforcement Learning for Autonomous Penetration Testing using A3C, Q-learning and DQN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Daniel Reti, Evridiki V. Ntagiou, Hans D. Schotten, Marcus Wallum, Norman Becker","submitted_at":"2024-07-22T14:17:29Z","abstract_excerpt":"Penetration testing is the process of searching for security weaknesses by simulating an attack. It is usually performed by experienced professionals, where scanning and attack tools are applied. By automating the execution of such tools, the need for human interaction and decision-making could be reduced. In this work, a Network Attack Simulator (NASim) was used as an environment to train reinforcement learning agents to solve three predefined security scenarios. These scenarios cover techniques of exploitation, post-exploitation and wiretapping. A large hyperparameter grid search was perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15656","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/2407.15656/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":"2407.15656","created_at":"2026-07-05T08:46:59.386673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15656v1","created_at":"2026-07-05T08:46:59.386673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15656","created_at":"2026-07-05T08:46:59.386673+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOROJ6QCGJ5J","created_at":"2026-07-05T08:46:59.386673+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOROJ6QCGJ5JFB5L","created_at":"2026-07-05T08:46:59.386673+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOROJ6QC","created_at":"2026-07-05T08:46:59.386673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05567","citing_title":"ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24949","citing_title":"APT-Agent: Automated Penetration Testing using Large Language Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ","json":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ.json","graph_json":"https://pith.science/api/pith-number/JOROJ6QCGJ5JFB5LC2OARRLZNJ/graph.json","events_json":"https://pith.science/api/pith-number/JOROJ6QCGJ5JFB5LC2OARRLZNJ/events.json","paper":"https://pith.science/paper/JOROJ6QC"},"agent_actions":{"view_html":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ","download_json":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ.json","view_paper":"https://pith.science/paper/JOROJ6QC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15656&json=true","fetch_graph":"https://pith.science/api/pith-number/JOROJ6QCGJ5JFB5LC2OARRLZNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JOROJ6QCGJ5JFB5LC2OARRLZNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ/action/storage_attestation","attest_author":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ/action/author_attestation","sign_citation":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ/action/citation_signature","submit_replication":"https://pith.science/pith/JOROJ6QCGJ5JFB5LC2OARRLZNJ/action/replication_record"}},"created_at":"2026-07-05T08:46:59.386673+00:00","updated_at":"2026-07-05T08:46:59.386673+00:00"}