{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FPFR4I7INJP4ZOSVYNQSNVMRYH","short_pith_number":"pith:FPFR4I7I","schema_version":"1.0","canonical_sha256":"2bcb1e23e86a5fccba55c36126d591c1db387a19340c7952f260dfa659554079","source":{"kind":"arxiv","id":"2007.10457","version":1},"attestation_state":"computed","paper":{"title":"Multi-agent Reinforcement Learning in Bayesian Stackelberg Markov Games for Adaptive Moving Target Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.GT","authors_text":"Sailik Sengupta, Subbarao Kambhampati","submitted_at":"2020-07-20T20:34:53Z","abstract_excerpt":"The field of cybersecurity has mostly been a cat-and-mouse game with the discovery of new attacks leading the way. To take away an attacker's advantage of reconnaissance, researchers have proposed proactive defense methods such as Moving Target Defense (MTD). To find good movement strategies, researchers have modeled MTD as leader-follower games between the defender and a cyber-adversary. We argue that existing models are inadequate in sequential settings when there is incomplete information about a rational adversary and yield sub-optimal movement strategies. Further, while there exists an ar"},"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":"2007.10457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2020-07-20T20:34:53Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"f7748d00c998f013de35e9da8f6171b87b6d7bf111ec0c1ae3950ce8f55d027a","abstract_canon_sha256":"d379227dc972bff9a199d7cd70539d8a99d546157957e7673ab8dd55c0c1fa5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:38.764927Z","signature_b64":"+/AP19WqAgPdpl/Y3UNDlcAS5YvvfCkl7r3HyYo633v0OyFOP0crwqITcoinkdR/nRkwNVaWo3EMedLOFwErBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bcb1e23e86a5fccba55c36126d591c1db387a19340c7952f260dfa659554079","last_reissued_at":"2026-07-05T01:20:38.764445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:38.764445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-agent Reinforcement Learning in Bayesian Stackelberg Markov Games for Adaptive Moving Target Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.GT","authors_text":"Sailik Sengupta, Subbarao Kambhampati","submitted_at":"2020-07-20T20:34:53Z","abstract_excerpt":"The field of cybersecurity has mostly been a cat-and-mouse game with the discovery of new attacks leading the way. To take away an attacker's advantage of reconnaissance, researchers have proposed proactive defense methods such as Moving Target Defense (MTD). To find good movement strategies, researchers have modeled MTD as leader-follower games between the defender and a cyber-adversary. We argue that existing models are inadequate in sequential settings when there is incomplete information about a rational adversary and yield sub-optimal movement strategies. Further, while there exists an ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10457","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/2007.10457/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":"2007.10457","created_at":"2026-07-05T01:20:38.764507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.10457v1","created_at":"2026-07-05T01:20:38.764507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10457","created_at":"2026-07-05T01:20:38.764507+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPFR4I7INJP4","created_at":"2026-07-05T01:20:38.764507+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPFR4I7INJP4ZOSV","created_at":"2026-07-05T01:20:38.764507+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPFR4I7I","created_at":"2026-07-05T01:20:38.764507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30136","citing_title":"Robust Strategic Classification under Decision-Dependent Cost Uncertainty","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08268","citing_title":"Insider Attacks in Multi-Agent LLM Consensus Systems","ref_index":212,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH","json":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH.json","graph_json":"https://pith.science/api/pith-number/FPFR4I7INJP4ZOSVYNQSNVMRYH/graph.json","events_json":"https://pith.science/api/pith-number/FPFR4I7INJP4ZOSVYNQSNVMRYH/events.json","paper":"https://pith.science/paper/FPFR4I7I"},"agent_actions":{"view_html":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH","download_json":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH.json","view_paper":"https://pith.science/paper/FPFR4I7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.10457&json=true","fetch_graph":"https://pith.science/api/pith-number/FPFR4I7INJP4ZOSVYNQSNVMRYH/graph.json","fetch_events":"https://pith.science/api/pith-number/FPFR4I7INJP4ZOSVYNQSNVMRYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH/action/storage_attestation","attest_author":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH/action/author_attestation","sign_citation":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH/action/citation_signature","submit_replication":"https://pith.science/pith/FPFR4I7INJP4ZOSVYNQSNVMRYH/action/replication_record"}},"created_at":"2026-07-05T01:20:38.764507+00:00","updated_at":"2026-07-05T01:20:38.764507+00:00"}