{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3WX4WDREKET6B74CIVFCD5AWY7","short_pith_number":"pith:3WX4WDRE","schema_version":"1.0","canonical_sha256":"ddafcb0e245127e0ff82454a21f416c7d98ee45bfd3a08368d51654e4a66be04","source":{"kind":"arxiv","id":"2411.15222","version":1},"attestation_state":"computed","paper":{"title":"Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Huayang Huang (1), Ke Zhao (1), Miao Li (1), Yu Wu (1) ((1) Wuhan University)","submitted_at":"2024-11-21T02:46:04Z","abstract_excerpt":"Language-conditioned robotic learning has significantly enhanced robot adaptability by enabling a single model to execute diverse tasks in response to verbal commands. Despite these advancements, security vulnerabilities within this domain remain largely unexplored. This paper addresses this gap by proposing a novel adversarial prompt attack tailored to language-conditioned robotic models. Our approach involves crafting a universal adversarial prefix that induces the model to perform unintended actions when added to any original prompt. We demonstrate that existing adversarial techniques exhib"},"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":"2411.15222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T02:46:04Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"b62a7e122696b418a96f05a04bbb83bdfec3595671bdbb9f62d1b4edc3ae18b3","abstract_canon_sha256":"4b39cacd0776beea7738e03c83dab829367246b6c2178a2aa8f2aed019620bcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:31.438579Z","signature_b64":"kOV2pTr0hzvEIvY718ISMTbodn9LcLAcr7UYb38KJ7PfgIvqgO/iCJFCkoyPjHpznaxoeSb7LUds93zqLPgQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddafcb0e245127e0ff82454a21f416c7d98ee45bfd3a08368d51654e4a66be04","last_reissued_at":"2026-07-05T09:39:31.438125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:31.438125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Huayang Huang (1), Ke Zhao (1), Miao Li (1), Yu Wu (1) ((1) Wuhan University)","submitted_at":"2024-11-21T02:46:04Z","abstract_excerpt":"Language-conditioned robotic learning has significantly enhanced robot adaptability by enabling a single model to execute diverse tasks in response to verbal commands. Despite these advancements, security vulnerabilities within this domain remain largely unexplored. This paper addresses this gap by proposing a novel adversarial prompt attack tailored to language-conditioned robotic models. Our approach involves crafting a universal adversarial prefix that induces the model to perform unintended actions when added to any original prompt. We demonstrate that existing adversarial techniques exhib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15222","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/2411.15222/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":"2411.15222","created_at":"2026-07-05T09:39:31.438185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15222v1","created_at":"2026-07-05T09:39:31.438185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15222","created_at":"2026-07-05T09:39:31.438185+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WX4WDREKET6","created_at":"2026-07-05T09:39:31.438185+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WX4WDREKET6B74C","created_at":"2026-07-05T09:39:31.438185+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WX4WDRE","created_at":"2026-07-05T09:39:31.438185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.03698","citing_title":"How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7","json":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7.json","graph_json":"https://pith.science/api/pith-number/3WX4WDREKET6B74CIVFCD5AWY7/graph.json","events_json":"https://pith.science/api/pith-number/3WX4WDREKET6B74CIVFCD5AWY7/events.json","paper":"https://pith.science/paper/3WX4WDRE"},"agent_actions":{"view_html":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7","download_json":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7.json","view_paper":"https://pith.science/paper/3WX4WDRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15222&json=true","fetch_graph":"https://pith.science/api/pith-number/3WX4WDREKET6B74CIVFCD5AWY7/graph.json","fetch_events":"https://pith.science/api/pith-number/3WX4WDREKET6B74CIVFCD5AWY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7/action/storage_attestation","attest_author":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7/action/author_attestation","sign_citation":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7/action/citation_signature","submit_replication":"https://pith.science/pith/3WX4WDREKET6B74CIVFCD5AWY7/action/replication_record"}},"created_at":"2026-07-05T09:39:31.438185+00:00","updated_at":"2026-07-05T09:39:31.438185+00:00"}