{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OITE7S33LVTWM6DX2ZHCMAEX2C","short_pith_number":"pith:OITE7S33","schema_version":"1.0","canonical_sha256":"72264fcb7b5d67667877d64e260097d0b0871686dc35127a53bb9dcc8048f742","source":{"kind":"arxiv","id":"2505.13528","version":1},"attestation_state":"computed","paper":{"title":"LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Dongsheng Li, Guangping Zhang, Hansu Gu, Jiahao Liu, Li Shang, Mingzhe Han, Ning Gu, Peng Zhang, Shengkang Gu, Tun Lu","submitted_at":"2025-05-18T04:40:34Z","abstract_excerpt":"Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies often rely on simplistic heuristics, require access to internal RS data, and overlook the manipulation potential of textual reviews. In this work, we introduce Agent4SR, a novel framework that leverages Large Language Model (LLM)-based agents to perform low-knowledge, high-impact shilling attacks through both rating and review generation. Agent4SR simulates realistic user behavior by orchestrating adversarial interacti"},"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":"2505.13528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-18T04:40:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef81b575c88bed5ade163b739a915ee3409cdc4c29cef673e72320f01fe7f024","abstract_canon_sha256":"62ca2248350451fbd5d564d594d92ef3b0f933751555ca3c586ba6af54a8d4a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:47.372984Z","signature_b64":"/3HIYbevcDCb8AyYVnuaxVAHSiG2CeULAD0qjTKwut7aS8UTS5OrqlWF2s05bK0B51392SY1igWAQDbHccv+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72264fcb7b5d67667877d64e260097d0b0871686dc35127a53bb9dcc8048f742","last_reissued_at":"2026-07-05T11:05:47.372415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:47.372415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Dongsheng Li, Guangping Zhang, Hansu Gu, Jiahao Liu, Li Shang, Mingzhe Han, Ning Gu, Peng Zhang, Shengkang Gu, Tun Lu","submitted_at":"2025-05-18T04:40:34Z","abstract_excerpt":"Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies often rely on simplistic heuristics, require access to internal RS data, and overlook the manipulation potential of textual reviews. In this work, we introduce Agent4SR, a novel framework that leverages Large Language Model (LLM)-based agents to perform low-knowledge, high-impact shilling attacks through both rating and review generation. Agent4SR simulates realistic user behavior by orchestrating adversarial interacti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13528","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/2505.13528/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":"2505.13528","created_at":"2026-07-05T11:05:47.372479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13528v1","created_at":"2026-07-05T11:05:47.372479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13528","created_at":"2026-07-05T11:05:47.372479+00:00"},{"alias_kind":"pith_short_12","alias_value":"OITE7S33LVTW","created_at":"2026-07-05T11:05:47.372479+00:00"},{"alias_kind":"pith_short_16","alias_value":"OITE7S33LVTWM6DX","created_at":"2026-07-05T11:05:47.372479+00:00"},{"alias_kind":"pith_short_8","alias_value":"OITE7S33","created_at":"2026-07-05T11:05:47.372479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00540","citing_title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23640","citing_title":"Prompt-Unknown Promotion Attacks against LLM-based Sequential Recommender Systems","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C","json":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C.json","graph_json":"https://pith.science/api/pith-number/OITE7S33LVTWM6DX2ZHCMAEX2C/graph.json","events_json":"https://pith.science/api/pith-number/OITE7S33LVTWM6DX2ZHCMAEX2C/events.json","paper":"https://pith.science/paper/OITE7S33"},"agent_actions":{"view_html":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C","download_json":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C.json","view_paper":"https://pith.science/paper/OITE7S33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13528&json=true","fetch_graph":"https://pith.science/api/pith-number/OITE7S33LVTWM6DX2ZHCMAEX2C/graph.json","fetch_events":"https://pith.science/api/pith-number/OITE7S33LVTWM6DX2ZHCMAEX2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C/action/storage_attestation","attest_author":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C/action/author_attestation","sign_citation":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C/action/citation_signature","submit_replication":"https://pith.science/pith/OITE7S33LVTWM6DX2ZHCMAEX2C/action/replication_record"}},"created_at":"2026-07-05T11:05:47.372479+00:00","updated_at":"2026-07-05T11:05:47.372479+00:00"}