{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OZXCCX6VVN65RYBBCPR65ZB7E4","short_pith_number":"pith:OZXCCX6V","schema_version":"1.0","canonical_sha256":"766e215fd5ab7dd8e02113e3eee43f271f83c19eb37436ae5e33be4d26668be2","source":{"kind":"arxiv","id":"2412.13666","version":2},"attestation_state":"computed","paper":{"title":"Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Aneta Zugecova, Dominik Macko, Ivan Srba, Jakub Kopal, Katarina Marcincinova, Matus Mesarcik, Robert Moro","submitted_at":"2024-12-18T09:48:53Z","abstract_excerpt":"The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be effectively misused for generating disinformation news articles following predefined narratives. Their capabilities to generate personalized (in various aspects) content have also been evaluated and mostly found usable. However, a combination of personalization and disinformation abilities of LLMs has not been comprehensively studied yet. Such a dangerous combinatio"},"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":"2412.13666","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T09:48:53Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"0283038d4d77963fe75d6e8f0bb0e6a5e49cc9fa9a06189b65c0b1482999eec8","abstract_canon_sha256":"2c243951b393b000c95b60349130d280aefe5da716eef8b5d1cea0a6fcf669a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:08.735815Z","signature_b64":"hPbV8o9f+x30XGc6MErHGq2+wrNmdy/2z7sLO9/qVkaRbDplr6Xw6p3xP6lL65l2oGQpQcxkWBxwfuTc7pUCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"766e215fd5ab7dd8e02113e3eee43f271f83c19eb37436ae5e33be4d26668be2","last_reissued_at":"2026-07-05T11:43:08.735383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:08.735383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Aneta Zugecova, Dominik Macko, Ivan Srba, Jakub Kopal, Katarina Marcincinova, Matus Mesarcik, Robert Moro","submitted_at":"2024-12-18T09:48:53Z","abstract_excerpt":"The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be effectively misused for generating disinformation news articles following predefined narratives. Their capabilities to generate personalized (in various aspects) content have also been evaluated and mostly found usable. However, a combination of personalization and disinformation abilities of LLMs has not been comprehensively studied yet. Such a dangerous combinatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13666","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/2412.13666/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":"2412.13666","created_at":"2026-07-05T11:43:08.735438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13666v2","created_at":"2026-07-05T11:43:08.735438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13666","created_at":"2026-07-05T11:43:08.735438+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZXCCX6VVN65","created_at":"2026-07-05T11:43:08.735438+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZXCCX6VVN65RYBB","created_at":"2026-07-05T11:43:08.735438+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZXCCX6V","created_at":"2026-07-05T11:43:08.735438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18889","citing_title":"Security Concerns for Large Language Models: A Survey","ref_index":78,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4","json":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4.json","graph_json":"https://pith.science/api/pith-number/OZXCCX6VVN65RYBBCPR65ZB7E4/graph.json","events_json":"https://pith.science/api/pith-number/OZXCCX6VVN65RYBBCPR65ZB7E4/events.json","paper":"https://pith.science/paper/OZXCCX6V"},"agent_actions":{"view_html":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4","download_json":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4.json","view_paper":"https://pith.science/paper/OZXCCX6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13666&json=true","fetch_graph":"https://pith.science/api/pith-number/OZXCCX6VVN65RYBBCPR65ZB7E4/graph.json","fetch_events":"https://pith.science/api/pith-number/OZXCCX6VVN65RYBBCPR65ZB7E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4/action/storage_attestation","attest_author":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4/action/author_attestation","sign_citation":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4/action/citation_signature","submit_replication":"https://pith.science/pith/OZXCCX6VVN65RYBBCPR65ZB7E4/action/replication_record"}},"created_at":"2026-07-05T11:43:08.735438+00:00","updated_at":"2026-07-05T11:43:08.735438+00:00"}