{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SGUMAJX2I4FWR6FCJVARJOXMQY","short_pith_number":"pith:SGUMAJX2","schema_version":"1.0","canonical_sha256":"91a8c026fa470b68f8a24d4114baec863871e608c6ec5aaceb8e8d75a8edce0b","source":{"kind":"arxiv","id":"2602.00364","version":4},"attestation_state":"computed","paper":{"title":"\"Someone Hid It\": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Chenxiao Yu, Defu Cao, Jiate Li, Li Li, Ryan A. Rossi, Tiannuo Yang, Wei Yang, Xiyang Hu, Yan Liu, Yuehan Qin, Yue Zhao","submitted_at":"2026-01-30T22:28:04Z","abstract_excerpt":"Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated that such LLM-based Retrieval (LLMR) is vulnerable to adversarial attacks, which manipulates documents by token-level injections and enables adversaries to either boost or diminish these documents in retrieval tasks. However, existing attack studies mainly (1) presume a known query is given to the attacker, and (2) highly rely on access to the victim model's "},"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":"2602.00364","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-01-30T22:28:04Z","cross_cats_sorted":[],"title_canon_sha256":"8455c4d19cdf8ee7bafa82c7b3f9930da4b8a61df5bea1211b2f7d6a8a73d434","abstract_canon_sha256":"31c9f04a39149619ec7c8b40967d7b74c34d4acf58ee85177d448a9da8dcee4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:32.985806Z","signature_b64":"3scV2Bg5sWJ9TXk7fibu3pSHvhCXCgofxUAEPQrsrz3gfEvNfOz14Bz5iwNUsrKpoWa6icUv4Ep7s2YuBppXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91a8c026fa470b68f8a24d4114baec863871e608c6ec5aaceb8e8d75a8edce0b","last_reissued_at":"2026-05-20T00:00:32.985139Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:32.985139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Someone Hid It\": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Chenxiao Yu, Defu Cao, Jiate Li, Li Li, Ryan A. Rossi, Tiannuo Yang, Wei Yang, Xiyang Hu, Yan Liu, Yuehan Qin, Yue Zhao","submitted_at":"2026-01-30T22:28:04Z","abstract_excerpt":"Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated that such LLM-based Retrieval (LLMR) is vulnerable to adversarial attacks, which manipulates documents by token-level injections and enables adversaries to either boost or diminish these documents in retrieval tasks. However, existing attack studies mainly (1) presume a known query is given to the attacker, and (2) highly rely on access to the victim model's "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00364","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/2602.00364/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":"2602.00364","created_at":"2026-05-20T00:00:32.985251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.00364v4","created_at":"2026-05-20T00:00:32.985251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00364","created_at":"2026-05-20T00:00:32.985251+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGUMAJX2I4FW","created_at":"2026-05-20T00:00:32.985251+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGUMAJX2I4FWR6FC","created_at":"2026-05-20T00:00:32.985251+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGUMAJX2","created_at":"2026-05-20T00:00:32.985251+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/SGUMAJX2I4FWR6FCJVARJOXMQY","json":"https://pith.science/pith/SGUMAJX2I4FWR6FCJVARJOXMQY.json","graph_json":"https://pith.science/api/pith-number/SGUMAJX2I4FWR6FCJVARJOXMQY/graph.json","events_json":"https://pith.science/api/pith-number/SGUMAJX2I4FWR6FCJVARJOXMQY/events.json","paper":"https://pith.science/paper/SGUMAJX2"},"agent_actions":{"view_html":"https://pith.science/pith/SGUMAJX2I4FWR6FCJVARJOXMQY","download_json":"https://pith.science/pith/SGUMAJX2I4FWR6FCJVARJOXMQY.json","view_paper":"https://pith.science/paper/SGUMAJX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.00364&json=true","fetch_graph":"https://pith.science/api/pith-number/SGUMAJX2I4FWR6FCJVARJOXMQY/graph.json","fetch_events":"https://pith.science/api/pith-number/SGUMAJX2I4FWR6FCJVARJOXMQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGUMAJX2I4FWR6FCJVARJOXMQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGUMAJX2I4FWR6FCJVARJOXMQY/action/storage_attestation","attest_author":"https://pith.science/pith/SGUMAJX2I4FWR6FCJVARJOXMQY/action/author_attestation","sign_citation":"https://pith.science/pith/SGUMAJX2I4FWR6FCJVARJOXMQY/action/citation_signature","submit_replication":"https://pith.science/pith/SGUMAJX2I4FWR6FCJVARJOXMQY/action/replication_record"}},"created_at":"2026-05-20T00:00:32.985251+00:00","updated_at":"2026-05-20T00:00:32.985251+00:00"}