{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5LWXDEV3A4EG7OZZ6QIVPOOCNZ","short_pith_number":"pith:5LWXDEV3","canonical_record":{"source":{"id":"2404.14461","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T05:08:53Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"3c304c274194e7625350274559aef3a19edda3990e70af0541a1f77f801facc3","abstract_canon_sha256":"23ee86bd3a155536d7cc92ce2b40989062f548f9df1b175b107a99d9f38d81b2"},"schema_version":"1.0"},"canonical_sha256":"eaed7192bb07086fbb39f41157b9c26e5835ead4ee1d08ec6eefb8c213cd8132","source":{"kind":"arxiv","id":"2404.14461","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14461","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14461v2","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14461","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"5LWXDEV3A4EG","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"5LWXDEV3A4EG7OZZ","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"5LWXDEV3","created_at":"2026-07-05T08:28:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5LWXDEV3A4EG7OZZ6QIVPOOCNZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.14461","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T05:08:53Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"3c304c274194e7625350274559aef3a19edda3990e70af0541a1f77f801facc3","abstract_canon_sha256":"23ee86bd3a155536d7cc92ce2b40989062f548f9df1b175b107a99d9f38d81b2"},"schema_version":"1.0"},"canonical_sha256":"eaed7192bb07086fbb39f41157b9c26e5835ead4ee1d08ec6eefb8c213cd8132","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:09.381951Z","signature_b64":"3QMERy/Gy+G/B5v1mk2sg+DkcQW0yRACAEngDXlku2w2WPARAMl+q1S1Nasvxdc+ZItm98NjKW7Leu7zwvy6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaed7192bb07086fbb39f41157b9c26e5835ead4ee1d08ec6eefb8c213cd8132","last_reissued_at":"2026-07-05T08:28:09.381530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:09.381530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.14461","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/X/bYXD6HH4YeUDV0RzgepGrB4rrrSJTsKVp0VzbVGj85Fd6uzBU7LzwU46KQsSarek2X2fC5Wc1/Dkn0fQoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:56:01.704557Z"},"content_sha256":"8d10696fe6ebb700a24d6428847dfb88b71e794422832afe5b1b70423c87e77a","schema_version":"1.0","event_id":"sha256:8d10696fe6ebb700a24d6428847dfb88b71e794422832afe5b1b70423c87e77a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5LWXDEV3A4EG7OZZ6QIVPOOCNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Florian Tram\\`er, Francesco Croce, Javier Rando, Kry\\v{s}tof Mitka, Maksym Andriushchenko, Nicolas Flammarion, Stepan Shabalin","submitted_at":"2024-04-22T05:08:53Z","abstract_excerpt":"Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14461","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/2404.14461/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/RT0I9qAkySRHPakAbs9BgNLm0vHm/6KOKUWUt0JlY4+PVqFKWVbANlb+23IsPm1ujfrX8KmrVF2F3paRbnACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:56:01.704929Z"},"content_sha256":"4c7b3442f4f5b8c048cb6d4b713c1d72b5bf7d86aefa66d35128c426a4678df9","schema_version":"1.0","event_id":"sha256:4c7b3442f4f5b8c048cb6d4b713c1d72b5bf7d86aefa66d35128c426a4678df9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5LWXDEV3A4EG7OZZ6QIVPOOCNZ/bundle.json","state_url":"https://pith.science/pith/5LWXDEV3A4EG7OZZ6QIVPOOCNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5LWXDEV3A4EG7OZZ6QIVPOOCNZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T03:56:01Z","links":{"resolver":"https://pith.science/pith/5LWXDEV3A4EG7OZZ6QIVPOOCNZ","bundle":"https://pith.science/pith/5LWXDEV3A4EG7OZZ6QIVPOOCNZ/bundle.json","state":"https://pith.science/pith/5LWXDEV3A4EG7OZZ6QIVPOOCNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5LWXDEV3A4EG7OZZ6QIVPOOCNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5LWXDEV3A4EG7OZZ6QIVPOOCNZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"23ee86bd3a155536d7cc92ce2b40989062f548f9df1b175b107a99d9f38d81b2","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T05:08:53Z","title_canon_sha256":"3c304c274194e7625350274559aef3a19edda3990e70af0541a1f77f801facc3"},"schema_version":"1.0","source":{"id":"2404.14461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.14461","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.14461v2","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14461","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"5LWXDEV3A4EG","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"5LWXDEV3A4EG7OZZ","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"5LWXDEV3","created_at":"2026-07-05T08:28:09Z"}],"graph_snapshots":[{"event_id":"sha256:4c7b3442f4f5b8c048cb6d4b713c1d72b5bf7d86aefa66d35128c426a4678df9","target":"graph","created_at":"2026-07-05T08:28:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.14461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language ","authors_text":"Florian Tram\\`er, Francesco Croce, Javier Rando, Kry\\v{s}tof Mitka, Maksym Andriushchenko, Nicolas Flammarion, Stepan Shabalin","cross_cats":["cs.AI","cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T05:08:53Z","title":"Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14461","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8d10696fe6ebb700a24d6428847dfb88b71e794422832afe5b1b70423c87e77a","target":"record","created_at":"2026-07-05T08:28:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"23ee86bd3a155536d7cc92ce2b40989062f548f9df1b175b107a99d9f38d81b2","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T05:08:53Z","title_canon_sha256":"3c304c274194e7625350274559aef3a19edda3990e70af0541a1f77f801facc3"},"schema_version":"1.0","source":{"id":"2404.14461","kind":"arxiv","version":2}},"canonical_sha256":"eaed7192bb07086fbb39f41157b9c26e5835ead4ee1d08ec6eefb8c213cd8132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eaed7192bb07086fbb39f41157b9c26e5835ead4ee1d08ec6eefb8c213cd8132","first_computed_at":"2026-07-05T08:28:09.381530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:09.381530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3QMERy/Gy+G/B5v1mk2sg+DkcQW0yRACAEngDXlku2w2WPARAMl+q1S1Nasvxdc+ZItm98NjKW7Leu7zwvy6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:09.381951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.14461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d10696fe6ebb700a24d6428847dfb88b71e794422832afe5b1b70423c87e77a","sha256:4c7b3442f4f5b8c048cb6d4b713c1d72b5bf7d86aefa66d35128c426a4678df9"],"state_sha256":"bdf324bfa4095be0304c1fda8cefdc604f648d6a6226d8cc658e9fc8e5367ac4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/4FPoslImsPdunQF15m1FaS4iSVbc9wXaIenS2IXcpqFHqf0ZkP5yBWLKDcjbQY4acIrtcJp7eqOfK8GblI7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:56:01.706932Z","bundle_sha256":"bbf9b855c07bc1e8bb98542f5ce99a6b40da71cb1ac66cb5d0674fb2fd224407"}}