{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UDJZ76SFNU3MLANB4UGA4HRZ5C","short_pith_number":"pith:UDJZ76SF","schema_version":"1.0","canonical_sha256":"a0d39ffa456d36c581a1e50c0e1e39e89c2cd13f38fcf9b72bf0ed68accc6ec4","source":{"kind":"arxiv","id":"2303.02725","version":4},"attestation_state":"computed","paper":{"title":"Local Environment Poisoning Attacks on Federated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Evelyn Ma, Praneet Rathi, S. Rasoul Etesami","submitted_at":"2023-03-05T17:44:23Z","abstract_excerpt":"Federated learning (FL) has become a popular tool for solving traditional Reinforcement Learning (RL) tasks. The multi-agent structure addresses the major concern of data-hungry in traditional RL, while the federated mechanism protects the data privacy of individual agents. However, the federated mechanism also exposes the system to poisoning by malicious agents that can mislead the trained policy. Despite the advantage brought by FL, the vulnerability of Federated Reinforcement Learning (FRL) has not been well-studied before. In this work, we propose a general framework to characterize FRL po"},"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":"2303.02725","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-05T17:44:23Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"6de4acdc72e28e2a705d86d28bce615b7083b273a0ca63d46be6c40c2d4185b0","abstract_canon_sha256":"1888f732ae19244328548f1a35af70d87c2ec9c282b4710c2f7e9cd5a0b9fa6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:18.735540Z","signature_b64":"PpBvAoWJhse6GnJ8/Fm9kwRwL8TAHO3xu/4oPUqDLqQa7Meb2C36ORllT9hXJAbF6xkknsXnYwGEbsWp9d/HCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0d39ffa456d36c581a1e50c0e1e39e89c2cd13f38fcf9b72bf0ed68accc6ec4","last_reissued_at":"2026-07-05T07:30:18.735021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:18.735021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Environment Poisoning Attacks on Federated Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Evelyn Ma, Praneet Rathi, S. Rasoul Etesami","submitted_at":"2023-03-05T17:44:23Z","abstract_excerpt":"Federated learning (FL) has become a popular tool for solving traditional Reinforcement Learning (RL) tasks. The multi-agent structure addresses the major concern of data-hungry in traditional RL, while the federated mechanism protects the data privacy of individual agents. However, the federated mechanism also exposes the system to poisoning by malicious agents that can mislead the trained policy. Despite the advantage brought by FL, the vulnerability of Federated Reinforcement Learning (FRL) has not been well-studied before. In this work, we propose a general framework to characterize FRL po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02725","kind":"arxiv","version":4},"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/2303.02725/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":"2303.02725","created_at":"2026-07-05T07:30:18.735078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02725v4","created_at":"2026-07-05T07:30:18.735078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02725","created_at":"2026-07-05T07:30:18.735078+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDJZ76SFNU3M","created_at":"2026-07-05T07:30:18.735078+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDJZ76SFNU3MLANB","created_at":"2026-07-05T07:30:18.735078+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDJZ76SF","created_at":"2026-07-05T07:30:18.735078+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/UDJZ76SFNU3MLANB4UGA4HRZ5C","json":"https://pith.science/pith/UDJZ76SFNU3MLANB4UGA4HRZ5C.json","graph_json":"https://pith.science/api/pith-number/UDJZ76SFNU3MLANB4UGA4HRZ5C/graph.json","events_json":"https://pith.science/api/pith-number/UDJZ76SFNU3MLANB4UGA4HRZ5C/events.json","paper":"https://pith.science/paper/UDJZ76SF"},"agent_actions":{"view_html":"https://pith.science/pith/UDJZ76SFNU3MLANB4UGA4HRZ5C","download_json":"https://pith.science/pith/UDJZ76SFNU3MLANB4UGA4HRZ5C.json","view_paper":"https://pith.science/paper/UDJZ76SF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02725&json=true","fetch_graph":"https://pith.science/api/pith-number/UDJZ76SFNU3MLANB4UGA4HRZ5C/graph.json","fetch_events":"https://pith.science/api/pith-number/UDJZ76SFNU3MLANB4UGA4HRZ5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDJZ76SFNU3MLANB4UGA4HRZ5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDJZ76SFNU3MLANB4UGA4HRZ5C/action/storage_attestation","attest_author":"https://pith.science/pith/UDJZ76SFNU3MLANB4UGA4HRZ5C/action/author_attestation","sign_citation":"https://pith.science/pith/UDJZ76SFNU3MLANB4UGA4HRZ5C/action/citation_signature","submit_replication":"https://pith.science/pith/UDJZ76SFNU3MLANB4UGA4HRZ5C/action/replication_record"}},"created_at":"2026-07-05T07:30:18.735078+00:00","updated_at":"2026-07-05T07:30:18.735078+00:00"}