{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3NJL3D5XO4CTHRQQMBJTTYGOE5","short_pith_number":"pith:3NJL3D5X","schema_version":"1.0","canonical_sha256":"db52bd8fb7770533c610605339e0ce2758f8fec7cd89c8a00494f89164b042d7","source":{"kind":"arxiv","id":"2406.13843","version":2},"attestation_state":"computed","paper":{"title":"Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Beth Goldberg, Iason Gabriel, Nahema Marchal, Rachel Xu, Rasmi Elasmar, William Isaac","submitted_at":"2024-06-19T21:11:17Z","abstract_excerpt":"Generative, multimodal artificial intelligence (GenAI) offers transformative potential across industries, but its misuse poses significant risks. Prior research has shed light on the potential of advanced AI systems to be exploited for malicious purposes. However, we still lack a concrete understanding of how GenAI models are specifically exploited or abused in practice, including the tactics employed to inflict harm. In this paper, we present a taxonomy of GenAI misuse tactics, informed by existing academic literature and a qualitative analysis of approximately 200 observed incidents of misus"},"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":"2406.13843","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-19T21:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"df4982c574773b9bf20b09579976e7fd7d1cb8dd5976850bfa494b5a0b2d95b0","abstract_canon_sha256":"4364eeac18a1cac33656353663e1a12b237f753f1c887b7a7c65249e98a6d63e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:04.750135Z","signature_b64":"BqF8qxgMge+JVrFGLjPxkOlChMtwiB+ZTOwtIda1D2lHiDJpDM/hlUjCuGhPbDBj346RLJ586x0geS/Zn7OFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db52bd8fb7770533c610605339e0ce2758f8fec7cd89c8a00494f89164b042d7","last_reissued_at":"2026-07-05T08:35:04.749696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:04.749696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Beth Goldberg, Iason Gabriel, Nahema Marchal, Rachel Xu, Rasmi Elasmar, William Isaac","submitted_at":"2024-06-19T21:11:17Z","abstract_excerpt":"Generative, multimodal artificial intelligence (GenAI) offers transformative potential across industries, but its misuse poses significant risks. Prior research has shed light on the potential of advanced AI systems to be exploited for malicious purposes. However, we still lack a concrete understanding of how GenAI models are specifically exploited or abused in practice, including the tactics employed to inflict harm. In this paper, we present a taxonomy of GenAI misuse tactics, informed by existing academic literature and a qualitative analysis of approximately 200 observed incidents of misus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13843","kind":"arxiv","version":2},"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/2406.13843/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":"2406.13843","created_at":"2026-07-05T08:35:04.749753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13843v2","created_at":"2026-07-05T08:35:04.749753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13843","created_at":"2026-07-05T08:35:04.749753+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NJL3D5XO4CT","created_at":"2026-07-05T08:35:04.749753+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NJL3D5XO4CTHRQQ","created_at":"2026-07-05T08:35:04.749753+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NJL3D5X","created_at":"2026-07-05T08:35:04.749753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.17270","citing_title":"Understanding U.S. Users' Security and Privacy Transparency Needs for Consumer-Facing Generative AI","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2606.31602","citing_title":"Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31602","citing_title":"Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17270","citing_title":"Understanding U.S. Users' Security and Privacy Transparency Needs for Consumer-Facing Generative AI","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5","json":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5.json","graph_json":"https://pith.science/api/pith-number/3NJL3D5XO4CTHRQQMBJTTYGOE5/graph.json","events_json":"https://pith.science/api/pith-number/3NJL3D5XO4CTHRQQMBJTTYGOE5/events.json","paper":"https://pith.science/paper/3NJL3D5X"},"agent_actions":{"view_html":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5","download_json":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5.json","view_paper":"https://pith.science/paper/3NJL3D5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13843&json=true","fetch_graph":"https://pith.science/api/pith-number/3NJL3D5XO4CTHRQQMBJTTYGOE5/graph.json","fetch_events":"https://pith.science/api/pith-number/3NJL3D5XO4CTHRQQMBJTTYGOE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5/action/storage_attestation","attest_author":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5/action/author_attestation","sign_citation":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5/action/citation_signature","submit_replication":"https://pith.science/pith/3NJL3D5XO4CTHRQQMBJTTYGOE5/action/replication_record"}},"created_at":"2026-07-05T08:35:04.749753+00:00","updated_at":"2026-07-05T08:35:04.749753+00:00"}