{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XMX24O5F6HMQXIMYOPQPMPTS2Q","short_pith_number":"pith:XMX24O5F","schema_version":"1.0","canonical_sha256":"bb2fae3ba5f1d90ba19873e0f63e72d4254f8af2e1072d783a951eaa57bff4dc","source":{"kind":"arxiv","id":"2211.14769","version":4},"attestation_state":"computed","paper":{"title":"Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","cs.CV"],"primary_cat":"cs.AI","authors_text":"Cihang Xie, Kaiwen Zhou, Xin Eric Wang, Yunchao Zhang, Zonglin Di","submitted_at":"2022-11-27T09:01:31Z","abstract_excerpt":"Federated embodied agent learning protects the data privacy of individual visual environments by keeping data locally at each client (the individual environment) during training. However, since the local data is inaccessible to the server under federated learning, attackers may easily poison the training data of the local client to build a backdoor in the agent without notice. Deploying such an agent raises the risk of potential harm to humans, as the attackers may easily navigate and control the agent as they wish via the backdoor. Towards Byzantine-robust federated embodied agent learning, i"},"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":"2211.14769","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-11-27T09:01:31Z","cross_cats_sorted":["cs.CL","cs.CR","cs.CV"],"title_canon_sha256":"1677ae8cf4112b04f28efb085c3741ca79463853e2beb77ce5371f469d9b3b52","abstract_canon_sha256":"5a986c09a6b0e2667d0622b139c1b6da95b09dfe9619a9fce2f87f28bb3cd6e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:45.708299Z","signature_b64":"YHWVogXZztpp4Mp7E2BZNsMdQgXiyGjfEbR2f27PzKYkNA53ItoAMAzh4pMzd2kIGsbptzOnWHpFBXJwPCSuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2fae3ba5f1d90ba19873e0f63e72d4254f8af2e1072d783a951eaa57bff4dc","last_reissued_at":"2026-07-05T07:56:45.707841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:45.707841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","cs.CV"],"primary_cat":"cs.AI","authors_text":"Cihang Xie, Kaiwen Zhou, Xin Eric Wang, Yunchao Zhang, Zonglin Di","submitted_at":"2022-11-27T09:01:31Z","abstract_excerpt":"Federated embodied agent learning protects the data privacy of individual visual environments by keeping data locally at each client (the individual environment) during training. However, since the local data is inaccessible to the server under federated learning, attackers may easily poison the training data of the local client to build a backdoor in the agent without notice. Deploying such an agent raises the risk of potential harm to humans, as the attackers may easily navigate and control the agent as they wish via the backdoor. Towards Byzantine-robust federated embodied agent learning, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14769","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/2211.14769/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":"2211.14769","created_at":"2026-07-05T07:56:45.707903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.14769v4","created_at":"2026-07-05T07:56:45.707903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14769","created_at":"2026-07-05T07:56:45.707903+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMX24O5F6HMQ","created_at":"2026-07-05T07:56:45.707903+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMX24O5F6HMQXIMY","created_at":"2026-07-05T07:56:45.707903+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMX24O5F","created_at":"2026-07-05T07:56:45.707903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05017","citing_title":"Position: Embodied AI Requires a Privacy-Utility Trade-off","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q","json":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q.json","graph_json":"https://pith.science/api/pith-number/XMX24O5F6HMQXIMYOPQPMPTS2Q/graph.json","events_json":"https://pith.science/api/pith-number/XMX24O5F6HMQXIMYOPQPMPTS2Q/events.json","paper":"https://pith.science/paper/XMX24O5F"},"agent_actions":{"view_html":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q","download_json":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q.json","view_paper":"https://pith.science/paper/XMX24O5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.14769&json=true","fetch_graph":"https://pith.science/api/pith-number/XMX24O5F6HMQXIMYOPQPMPTS2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/XMX24O5F6HMQXIMYOPQPMPTS2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q/action/storage_attestation","attest_author":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q/action/author_attestation","sign_citation":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q/action/citation_signature","submit_replication":"https://pith.science/pith/XMX24O5F6HMQXIMYOPQPMPTS2Q/action/replication_record"}},"created_at":"2026-07-05T07:56:45.707903+00:00","updated_at":"2026-07-05T07:56:45.707903+00:00"}