{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X3N5D6GCLGB7QCPQP4NYYRO4VQ","short_pith_number":"pith:X3N5D6GC","schema_version":"1.0","canonical_sha256":"bedbd1f8c25983f809f07f1b8c45dcac107faff4b717bec1b5bf2c8e0f510dba","source":{"kind":"arxiv","id":"2606.20752","version":1},"attestation_state":"computed","paper":{"title":"Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Ang Li, Ziba Parsons","submitted_at":"2026-06-18T03:25:22Z","abstract_excerpt":"Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent studies have revealed its vulnerability to backdoor attacks. Existing attacks typically require white-box access or label modification and focus on geometric attacks such as object disappearance or bounding-box manipulation. In this paper, we present Mirage, a black-box and clean-label backdoor attack against deep neural network-based LiDAR 3DOD. Mirage injects a small number of label-consistent poisoning samples into the training set, causing the"},"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":"2606.20752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T03:25:22Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"ef1d2cd56c702847aecd76c8f250cea76b78f4f024264f1cd4215b267e9c1de9","abstract_canon_sha256":"6acaa6664ddc15b5c3e886b21bcc4d7817d7fc94d5dab3b802f9e99ed89aafa7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:55.703771Z","signature_b64":"6fo0u25qCk4HGSG/uQDG8V1tIuiPeXAlSq5nXof2cSMjneFZgcBajtRyeDsetP3Zqt04cSdqhl5GnW8ki/OLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bedbd1f8c25983f809f07f1b8c45dcac107faff4b717bec1b5bf2c8e0f510dba","last_reissued_at":"2026-06-23T00:11:55.703367Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:55.703367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Ang Li, Ziba Parsons","submitted_at":"2026-06-18T03:25:22Z","abstract_excerpt":"Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent studies have revealed its vulnerability to backdoor attacks. Existing attacks typically require white-box access or label modification and focus on geometric attacks such as object disappearance or bounding-box manipulation. In this paper, we present Mirage, a black-box and clean-label backdoor attack against deep neural network-based LiDAR 3DOD. Mirage injects a small number of label-consistent poisoning samples into the training set, causing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20752","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/2606.20752/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":"2606.20752","created_at":"2026-06-23T00:11:55.703434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20752v1","created_at":"2026-06-23T00:11:55.703434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20752","created_at":"2026-06-23T00:11:55.703434+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3N5D6GCLGB7","created_at":"2026-06-23T00:11:55.703434+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3N5D6GCLGB7QCPQ","created_at":"2026-06-23T00:11:55.703434+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3N5D6GC","created_at":"2026-06-23T00:11:55.703434+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/X3N5D6GCLGB7QCPQP4NYYRO4VQ","json":"https://pith.science/pith/X3N5D6GCLGB7QCPQP4NYYRO4VQ.json","graph_json":"https://pith.science/api/pith-number/X3N5D6GCLGB7QCPQP4NYYRO4VQ/graph.json","events_json":"https://pith.science/api/pith-number/X3N5D6GCLGB7QCPQP4NYYRO4VQ/events.json","paper":"https://pith.science/paper/X3N5D6GC"},"agent_actions":{"view_html":"https://pith.science/pith/X3N5D6GCLGB7QCPQP4NYYRO4VQ","download_json":"https://pith.science/pith/X3N5D6GCLGB7QCPQP4NYYRO4VQ.json","view_paper":"https://pith.science/paper/X3N5D6GC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20752&json=true","fetch_graph":"https://pith.science/api/pith-number/X3N5D6GCLGB7QCPQP4NYYRO4VQ/graph.json","fetch_events":"https://pith.science/api/pith-number/X3N5D6GCLGB7QCPQP4NYYRO4VQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3N5D6GCLGB7QCPQP4NYYRO4VQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3N5D6GCLGB7QCPQP4NYYRO4VQ/action/storage_attestation","attest_author":"https://pith.science/pith/X3N5D6GCLGB7QCPQP4NYYRO4VQ/action/author_attestation","sign_citation":"https://pith.science/pith/X3N5D6GCLGB7QCPQP4NYYRO4VQ/action/citation_signature","submit_replication":"https://pith.science/pith/X3N5D6GCLGB7QCPQP4NYYRO4VQ/action/replication_record"}},"created_at":"2026-06-23T00:11:55.703434+00:00","updated_at":"2026-06-23T00:11:55.703434+00:00"}