{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WK2YWMB6ULHTHFM2IFWQ24SYAG","short_pith_number":"pith:WK2YWMB6","schema_version":"1.0","canonical_sha256":"b2b58b303ea2cf33959a416d0d725801a2a4a507e1f0ff2427a0ba09d897902b","source":{"kind":"arxiv","id":"2407.13757","version":1},"attestation_state":"computed","paper":{"title":"Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CL","authors_text":"Fan Zhang, Haotan Liu, Jiawei Liu, Qikai Cheng, Wei Lu, Xiaozhong Liu, Zhuo Chen","submitted_at":"2024-07-18T17:55:55Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is applied to solve hallucination problems and real-time constraints of large language models, but it also induces vulnerabilities against retrieval corruption attacks. Existing research mainly explores the unreliability of RAG in white-box and closed-domain QA tasks. In this paper, we aim to reveal the vulnerabilities of Retrieval-Enhanced Generative (RAG) models when faced with black-box attacks for opinion manipulation. We explore the impact of such attacks on user cognition and decision-making, providing new insight to enhance the reliability and securi"},"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":"2407.13757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T17:55:55Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"d7ac90fc31eb8b0cf4f3af0effad893f520b33ecd0b53b71b65f2539ebfb9852","abstract_canon_sha256":"b3e40c7306532f69888c49bc90ff25d30b0112e51cc677d0ca2dd4de99bc971e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:43.869392Z","signature_b64":"bUQUkP1oEDoPrrKM+DN460b2uIhEbOqyJYJ0+t0m+V3A49An+fKyeRxoYYu7UclO4Ia4RCKFVtfqTwZFNpjnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b58b303ea2cf33959a416d0d725801a2a4a507e1f0ff2427a0ba09d897902b","last_reissued_at":"2026-07-05T08:45:43.868954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:43.868954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CL","authors_text":"Fan Zhang, Haotan Liu, Jiawei Liu, Qikai Cheng, Wei Lu, Xiaozhong Liu, Zhuo Chen","submitted_at":"2024-07-18T17:55:55Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is applied to solve hallucination problems and real-time constraints of large language models, but it also induces vulnerabilities against retrieval corruption attacks. Existing research mainly explores the unreliability of RAG in white-box and closed-domain QA tasks. In this paper, we aim to reveal the vulnerabilities of Retrieval-Enhanced Generative (RAG) models when faced with black-box attacks for opinion manipulation. We explore the impact of such attacks on user cognition and decision-making, providing new insight to enhance the reliability and securi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13757","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/2407.13757/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":"2407.13757","created_at":"2026-07-05T08:45:43.869010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13757v1","created_at":"2026-07-05T08:45:43.869010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13757","created_at":"2026-07-05T08:45:43.869010+00:00"},{"alias_kind":"pith_short_12","alias_value":"WK2YWMB6ULHT","created_at":"2026-07-05T08:45:43.869010+00:00"},{"alias_kind":"pith_short_16","alias_value":"WK2YWMB6ULHTHFM2","created_at":"2026-07-05T08:45:43.869010+00:00"},{"alias_kind":"pith_short_8","alias_value":"WK2YWMB6","created_at":"2026-07-05T08:45:43.869010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08304","citing_title":"Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG","json":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG.json","graph_json":"https://pith.science/api/pith-number/WK2YWMB6ULHTHFM2IFWQ24SYAG/graph.json","events_json":"https://pith.science/api/pith-number/WK2YWMB6ULHTHFM2IFWQ24SYAG/events.json","paper":"https://pith.science/paper/WK2YWMB6"},"agent_actions":{"view_html":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG","download_json":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG.json","view_paper":"https://pith.science/paper/WK2YWMB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13757&json=true","fetch_graph":"https://pith.science/api/pith-number/WK2YWMB6ULHTHFM2IFWQ24SYAG/graph.json","fetch_events":"https://pith.science/api/pith-number/WK2YWMB6ULHTHFM2IFWQ24SYAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG/action/storage_attestation","attest_author":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG/action/author_attestation","sign_citation":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG/action/citation_signature","submit_replication":"https://pith.science/pith/WK2YWMB6ULHTHFM2IFWQ24SYAG/action/replication_record"}},"created_at":"2026-07-05T08:45:43.869010+00:00","updated_at":"2026-07-05T08:45:43.869010+00:00"}