{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CEIL7I3GBL73ZGJNNBWDWCFBYV","short_pith_number":"pith:CEIL7I3G","schema_version":"1.0","canonical_sha256":"1110bfa3660affbc992d686c3b08a1c54ff14ee2c88e58612121689d93d3b531","source":{"kind":"arxiv","id":"2411.09523","version":1},"attestation_state":"computed","paper":{"title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunyi Zhou, Ping He, Qingming Li, Rui Zeng, Shouling Ji, Songze Li, Ting Wang, Yiming Wang, Yingcai Wu, Yong Yang, Yunjun Gao, Yuyou Gan, Zhe Ma","submitted_at":"2024-11-14T15:40:04Z","abstract_excerpt":"With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives.\n  To help researchers gain a compreh"},"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":"2411.09523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-14T15:40:04Z","cross_cats_sorted":[],"title_canon_sha256":"07e58d8da9d39283da5505ee7aa5a802bad77111abd3d85fa37c8f2ae0be82fd","abstract_canon_sha256":"45044aea796d7813a150d479276d0cfc4fe5a800665175a97fe3ae8c1c875560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:28.178600Z","signature_b64":"r2kf4Nzi5GpuylrkFJ3/eSZw5pB+tBFHfDgdpBAVnwr0kX86Pd+fOEgcgtxO6I71QzSqJVmtp/S2QmEgxjTVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1110bfa3660affbc992d686c3b08a1c54ff14ee2c88e58612121689d93d3b531","last_reissued_at":"2026-07-05T09:35:28.178077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:28.178077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunyi Zhou, Ping He, Qingming Li, Rui Zeng, Shouling Ji, Songze Li, Ting Wang, Yiming Wang, Yingcai Wu, Yong Yang, Yunjun Gao, Yuyou Gan, Zhe Ma","submitted_at":"2024-11-14T15:40:04Z","abstract_excerpt":"With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives.\n  To help researchers gain a compreh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09523","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/2411.09523/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":"2411.09523","created_at":"2026-07-05T09:35:28.178142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09523v1","created_at":"2026-07-05T09:35:28.178142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09523","created_at":"2026-07-05T09:35:28.178142+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEIL7I3GBL73","created_at":"2026-07-05T09:35:28.178142+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEIL7I3GBL73ZGJN","created_at":"2026-07-05T09:35:28.178142+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEIL7I3G","created_at":"2026-07-05T09:35:28.178142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26627","citing_title":"Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09182","citing_title":"Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04317","citing_title":"Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04075","citing_title":"Large Language Models Hack Rewards, and Society","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10749","citing_title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":212,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17830","citing_title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18672","citing_title":"Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2508.08127","citing_title":"BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02900","citing_title":"Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02837","citing_title":"Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23278","citing_title":"Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22571","citing_title":"LARA: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07836","citing_title":"Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02255","citing_title":"On the Privacy of LLMs: An Ablation Study","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV","json":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV.json","graph_json":"https://pith.science/api/pith-number/CEIL7I3GBL73ZGJNNBWDWCFBYV/graph.json","events_json":"https://pith.science/api/pith-number/CEIL7I3GBL73ZGJNNBWDWCFBYV/events.json","paper":"https://pith.science/paper/CEIL7I3G"},"agent_actions":{"view_html":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV","download_json":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV.json","view_paper":"https://pith.science/paper/CEIL7I3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09523&json=true","fetch_graph":"https://pith.science/api/pith-number/CEIL7I3GBL73ZGJNNBWDWCFBYV/graph.json","fetch_events":"https://pith.science/api/pith-number/CEIL7I3GBL73ZGJNNBWDWCFBYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV/action/storage_attestation","attest_author":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV/action/author_attestation","sign_citation":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV/action/citation_signature","submit_replication":"https://pith.science/pith/CEIL7I3GBL73ZGJNNBWDWCFBYV/action/replication_record"}},"created_at":"2026-07-05T09:35:28.178142+00:00","updated_at":"2026-07-05T09:35:28.178142+00:00"}