{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F5VIRNTVFZ43KXT2WZ26QFQDZC","short_pith_number":"pith:F5VIRNTV","schema_version":"1.0","canonical_sha256":"2f6a88b6752e79b55e7ab675e81603c88a78d2f7750a66cdfcd1c21580da15a2","source":{"kind":"arxiv","id":"2502.02960","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model Adversarial Landscape Through the Lens of Attack Objectives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Alsharif Abuadbba, Kane Walter, Nan Wang, Yansong Gao","submitted_at":"2025-02-05T07:54:07Z","abstract_excerpt":"Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an unparalleled scale. However, LLMs are increasingly vulnerable to a range of adversarial attacks that threaten their privacy, reliability, security, and trustworthiness. These attacks can distort outputs, inject biases, leak sensitive information, or disrupt the normal functioning of LLMs, posing significant challenges across various applications.\n  In this paper, we provide a novel comprehensive analysis of the advers"},"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":"2502.02960","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-05T07:54:07Z","cross_cats_sorted":[],"title_canon_sha256":"6f2ebda1c4b83f71e75375fd5b6523e072ebbfec0a1ef23b015114cfe50627c9","abstract_canon_sha256":"3c9139b43960f3cf8c22b5b8b95bd33e37c49e3cac407f8e1869b1c8108fb5fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:57.515929Z","signature_b64":"WOt+CV23/AbTynWnC9hXydDYhMApLLPFHqS7Z2Bx0GYPhpP68xTXCcAJPRaG1G4rNsNHz/zRTzhjdJ+M+Bv2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f6a88b6752e79b55e7ab675e81603c88a78d2f7750a66cdfcd1c21580da15a2","last_reissued_at":"2026-07-05T10:09:57.515283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:57.515283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Adversarial Landscape Through the Lens of Attack Objectives","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Alsharif Abuadbba, Kane Walter, Nan Wang, Yansong Gao","submitted_at":"2025-02-05T07:54:07Z","abstract_excerpt":"Large Language Models (LLMs) represent a transformative leap in artificial intelligence, enabling the comprehension, generation, and nuanced interaction with human language on an unparalleled scale. However, LLMs are increasingly vulnerable to a range of adversarial attacks that threaten their privacy, reliability, security, and trustworthiness. These attacks can distort outputs, inject biases, leak sensitive information, or disrupt the normal functioning of LLMs, posing significant challenges across various applications.\n  In this paper, we provide a novel comprehensive analysis of the advers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02960","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/2502.02960/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":"2502.02960","created_at":"2026-07-05T10:09:57.515373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02960v1","created_at":"2026-07-05T10:09:57.515373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02960","created_at":"2026-07-05T10:09:57.515373+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5VIRNTVFZ43","created_at":"2026-07-05T10:09:57.515373+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5VIRNTVFZ43KXT2","created_at":"2026-07-05T10:09:57.515373+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5VIRNTV","created_at":"2026-07-05T10:09:57.515373+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/F5VIRNTVFZ43KXT2WZ26QFQDZC","json":"https://pith.science/pith/F5VIRNTVFZ43KXT2WZ26QFQDZC.json","graph_json":"https://pith.science/api/pith-number/F5VIRNTVFZ43KXT2WZ26QFQDZC/graph.json","events_json":"https://pith.science/api/pith-number/F5VIRNTVFZ43KXT2WZ26QFQDZC/events.json","paper":"https://pith.science/paper/F5VIRNTV"},"agent_actions":{"view_html":"https://pith.science/pith/F5VIRNTVFZ43KXT2WZ26QFQDZC","download_json":"https://pith.science/pith/F5VIRNTVFZ43KXT2WZ26QFQDZC.json","view_paper":"https://pith.science/paper/F5VIRNTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02960&json=true","fetch_graph":"https://pith.science/api/pith-number/F5VIRNTVFZ43KXT2WZ26QFQDZC/graph.json","fetch_events":"https://pith.science/api/pith-number/F5VIRNTVFZ43KXT2WZ26QFQDZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5VIRNTVFZ43KXT2WZ26QFQDZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5VIRNTVFZ43KXT2WZ26QFQDZC/action/storage_attestation","attest_author":"https://pith.science/pith/F5VIRNTVFZ43KXT2WZ26QFQDZC/action/author_attestation","sign_citation":"https://pith.science/pith/F5VIRNTVFZ43KXT2WZ26QFQDZC/action/citation_signature","submit_replication":"https://pith.science/pith/F5VIRNTVFZ43KXT2WZ26QFQDZC/action/replication_record"}},"created_at":"2026-07-05T10:09:57.515373+00:00","updated_at":"2026-07-05T10:09:57.515373+00:00"}