{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M6ICILQ2TIKRVNJ5SCFD6NVYTQ","short_pith_number":"pith:M6ICILQ2","schema_version":"1.0","canonical_sha256":"6790242e1a9a151ab53d908a3f36b89c1a8dde973a2c3b366008390780a4c173","source":{"kind":"arxiv","id":"2103.06473","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Federated Reinforcement Learning with Adversaries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aqeel Anwar, Arijit Raychowdhury","submitted_at":"2021-03-11T05:39:52Z","abstract_excerpt":"Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the Multi-task Federated Reinforcement Learning algorithms, where multiple collaborative agents in various environments are trying to maximize the sum of discounted return, in the presence of adversarial agents. We argue that the common attack methods are not guaranteed to carry out a successful attack on Multi-task Federated Reinforcement Learning and propose "},"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":"2103.06473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-11T05:39:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a359449c136ca104414e974ee79baba9aa8fc96e2b8f5cf1bec507ca277cbd73","abstract_canon_sha256":"ce9a5eede0f81a180f121090f0d97f74005fa9535ea2b68ca03962caa4df9443"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:09.379825Z","signature_b64":"8oltS+meVmI+gPD0hM2qwVV9qUMLsWB4Wa0eUJO53gVXLQSN2GJB9YIwLeiBKEToK81sbYwRk2QlyQhidqK4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6790242e1a9a151ab53d908a3f36b89c1a8dde973a2c3b366008390780a4c173","last_reissued_at":"2026-07-05T02:22:09.379377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:09.379377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Federated Reinforcement Learning with Adversaries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aqeel Anwar, Arijit Raychowdhury","submitted_at":"2021-03-11T05:39:52Z","abstract_excerpt":"Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the Multi-task Federated Reinforcement Learning algorithms, where multiple collaborative agents in various environments are trying to maximize the sum of discounted return, in the presence of adversarial agents. We argue that the common attack methods are not guaranteed to carry out a successful attack on Multi-task Federated Reinforcement Learning and propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06473","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/2103.06473/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":"2103.06473","created_at":"2026-07-05T02:22:09.379434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.06473v1","created_at":"2026-07-05T02:22:09.379434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06473","created_at":"2026-07-05T02:22:09.379434+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6ICILQ2TIKR","created_at":"2026-07-05T02:22:09.379434+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6ICILQ2TIKRVNJ5","created_at":"2026-07-05T02:22:09.379434+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6ICILQ2","created_at":"2026-07-05T02:22:09.379434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.09959","citing_title":"Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ","json":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ.json","graph_json":"https://pith.science/api/pith-number/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/graph.json","events_json":"https://pith.science/api/pith-number/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/events.json","paper":"https://pith.science/paper/M6ICILQ2"},"agent_actions":{"view_html":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ","download_json":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ.json","view_paper":"https://pith.science/paper/M6ICILQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.06473&json=true","fetch_graph":"https://pith.science/api/pith-number/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/action/storage_attestation","attest_author":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/action/author_attestation","sign_citation":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/action/citation_signature","submit_replication":"https://pith.science/pith/M6ICILQ2TIKRVNJ5SCFD6NVYTQ/action/replication_record"}},"created_at":"2026-07-05T02:22:09.379434+00:00","updated_at":"2026-07-05T02:22:09.379434+00:00"}