{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XLX6CFOQIMAPYOB5R62AVCDZFO","short_pith_number":"pith:XLX6CFOQ","schema_version":"1.0","canonical_sha256":"baefe115d04300fc383d8fb40a88792b874e297a4a91e6bd5ef63f9cfdb2eeeb","source":{"kind":"arxiv","id":"2412.02795","version":1},"attestation_state":"computed","paper":{"title":"Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Eric Slyman, Stefan Lee, Xiangxi Shi, Zijiao Yang","submitted_at":"2024-12-03T19:54:32Z","abstract_excerpt":"Assistive embodied agents that can be instructed in natural language to perform tasks in open-world environments have the potential to significantly impact labor tasks like manufacturing or in-home care -- benefiting the lives of those who come to depend on them. In this work, we consider how this benefit might be hijacked by local modifications in the appearance of the agent's operating environment. Specifically, we take the popular Vision-and-Language Navigation (VLN) task as a representative setting and develop a whitebox adversarial attack that optimizes a 3D attack object's appearance to "},"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":"2412.02795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T19:54:32Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"b2e6e4ee5191d1eeb18f88863829cddf46f79134d107a8a4d4d736c36836069f","abstract_canon_sha256":"2204d35cb029162f0a7145a02c0bf34dab099354f1e042fb1bad5891b2f4bb65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:19.622960Z","signature_b64":"pSRYFhiUVlH/407YGS+ZcI/MKZtzujv8C13piwKse6H1mU3H7Qlurfl+P9MeWNOohSfzwHYj+mQG6a9l5PfGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baefe115d04300fc383d8fb40a88792b874e297a4a91e6bd5ef63f9cfdb2eeeb","last_reissued_at":"2026-07-05T09:44:19.622560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:19.622560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Eric Slyman, Stefan Lee, Xiangxi Shi, Zijiao Yang","submitted_at":"2024-12-03T19:54:32Z","abstract_excerpt":"Assistive embodied agents that can be instructed in natural language to perform tasks in open-world environments have the potential to significantly impact labor tasks like manufacturing or in-home care -- benefiting the lives of those who come to depend on them. In this work, we consider how this benefit might be hijacked by local modifications in the appearance of the agent's operating environment. Specifically, we take the popular Vision-and-Language Navigation (VLN) task as a representative setting and develop a whitebox adversarial attack that optimizes a 3D attack object's appearance to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02795","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/2412.02795/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":"2412.02795","created_at":"2026-07-05T09:44:19.622617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02795v1","created_at":"2026-07-05T09:44:19.622617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02795","created_at":"2026-07-05T09:44:19.622617+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLX6CFOQIMAP","created_at":"2026-07-05T09:44:19.622617+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLX6CFOQIMAPYOB5","created_at":"2026-07-05T09:44:19.622617+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLX6CFOQ","created_at":"2026-07-05T09:44:19.622617+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/XLX6CFOQIMAPYOB5R62AVCDZFO","json":"https://pith.science/pith/XLX6CFOQIMAPYOB5R62AVCDZFO.json","graph_json":"https://pith.science/api/pith-number/XLX6CFOQIMAPYOB5R62AVCDZFO/graph.json","events_json":"https://pith.science/api/pith-number/XLX6CFOQIMAPYOB5R62AVCDZFO/events.json","paper":"https://pith.science/paper/XLX6CFOQ"},"agent_actions":{"view_html":"https://pith.science/pith/XLX6CFOQIMAPYOB5R62AVCDZFO","download_json":"https://pith.science/pith/XLX6CFOQIMAPYOB5R62AVCDZFO.json","view_paper":"https://pith.science/paper/XLX6CFOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02795&json=true","fetch_graph":"https://pith.science/api/pith-number/XLX6CFOQIMAPYOB5R62AVCDZFO/graph.json","fetch_events":"https://pith.science/api/pith-number/XLX6CFOQIMAPYOB5R62AVCDZFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLX6CFOQIMAPYOB5R62AVCDZFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLX6CFOQIMAPYOB5R62AVCDZFO/action/storage_attestation","attest_author":"https://pith.science/pith/XLX6CFOQIMAPYOB5R62AVCDZFO/action/author_attestation","sign_citation":"https://pith.science/pith/XLX6CFOQIMAPYOB5R62AVCDZFO/action/citation_signature","submit_replication":"https://pith.science/pith/XLX6CFOQIMAPYOB5R62AVCDZFO/action/replication_record"}},"created_at":"2026-07-05T09:44:19.622617+00:00","updated_at":"2026-07-05T09:44:19.622617+00:00"}