{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZRZVP3J2LPRZUB2LSYWN6U2BOU","short_pith_number":"pith:ZRZVP3J2","schema_version":"1.0","canonical_sha256":"cc7357ed3a5be39a074b962cdf5341750b871c2683298891d87c0cac24a61ccf","source":{"kind":"arxiv","id":"2407.20529","version":1},"attestation_state":"computed","paper":{"title":"Can LLMs be Fooled? Investigating Vulnerabilities in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"CJ Barberan, Jia He, Richard Anarfi, Sara Abdali","submitted_at":"2024-07-30T04:08:00Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has garnered significant popularity and wielded immense power across various domains within Natural Language Processing (NLP). While their capabilities are undeniably impressive, it is crucial to identify and scrutinize their vulnerabilities especially when those vulnerabilities can have costly consequences. One such LLM, trained to provide a concise summarization from medical documents could unequivocally leak personal patient data when prompted surreptitiously. This is just one of many unfortunate examples that have been unveiled and further researc"},"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":"2407.20529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-30T04:08:00Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"ccf056b59ae224e17458e382b34f51e97196cefc9c0558efb30d850ad34b32fa","abstract_canon_sha256":"68803a025864e418f96c8dc6adc567bd48f17742f9cf63df7af2bcec54e76626"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:00.065072Z","signature_b64":"t5UvmMhAFrJ4QpO23MLEQXauXdjLLV2JztT/klzhjlKOmwmu1R7bKBHgnz4bDO1kgZJcMutPvz/Inlm5m+meDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc7357ed3a5be39a074b962cdf5341750b871c2683298891d87c0cac24a61ccf","last_reissued_at":"2026-07-05T08:50:00.064605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:00.064605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs be Fooled? Investigating Vulnerabilities in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"CJ Barberan, Jia He, Richard Anarfi, Sara Abdali","submitted_at":"2024-07-30T04:08:00Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has garnered significant popularity and wielded immense power across various domains within Natural Language Processing (NLP). While their capabilities are undeniably impressive, it is crucial to identify and scrutinize their vulnerabilities especially when those vulnerabilities can have costly consequences. One such LLM, trained to provide a concise summarization from medical documents could unequivocally leak personal patient data when prompted surreptitiously. This is just one of many unfortunate examples that have been unveiled and further researc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20529","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/2407.20529/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":"2407.20529","created_at":"2026-07-05T08:50:00.064665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.20529v1","created_at":"2026-07-05T08:50:00.064665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20529","created_at":"2026-07-05T08:50:00.064665+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRZVP3J2LPRZ","created_at":"2026-07-05T08:50:00.064665+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRZVP3J2LPRZUB2L","created_at":"2026-07-05T08:50:00.064665+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRZVP3J2","created_at":"2026-07-05T08:50:00.064665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05961","citing_title":"Political Persuasion and Endorsement in Large Language Models","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU","json":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU.json","graph_json":"https://pith.science/api/pith-number/ZRZVP3J2LPRZUB2LSYWN6U2BOU/graph.json","events_json":"https://pith.science/api/pith-number/ZRZVP3J2LPRZUB2LSYWN6U2BOU/events.json","paper":"https://pith.science/paper/ZRZVP3J2"},"agent_actions":{"view_html":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU","download_json":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU.json","view_paper":"https://pith.science/paper/ZRZVP3J2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.20529&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRZVP3J2LPRZUB2LSYWN6U2BOU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRZVP3J2LPRZUB2LSYWN6U2BOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU/action/storage_attestation","attest_author":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU/action/author_attestation","sign_citation":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU/action/citation_signature","submit_replication":"https://pith.science/pith/ZRZVP3J2LPRZUB2LSYWN6U2BOU/action/replication_record"}},"created_at":"2026-07-05T08:50:00.064665+00:00","updated_at":"2026-07-05T08:50:00.064665+00:00"}