{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LI2XVZPVA7EMI4Y4APH3TYEUCI","short_pith_number":"pith:LI2XVZPV","canonical_record":{"source":{"id":"2501.18280","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T11:37:40Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"fd0f1739a5eaab9a77a620bb19a97c48544ea30e933428434c92ca0f8b602941","abstract_canon_sha256":"1fb69cd231489cb7d946e10b5908de15fd8c352491dc1189ce746107d6cd939f"},"schema_version":"1.0"},"canonical_sha256":"5a357ae5f507c8c4731c03cfb9e094123c0edd2a4acc0abe369ee87b7dcae07f","source":{"kind":"arxiv","id":"2501.18280","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18280","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18280v3","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18280","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"LI2XVZPVA7EM","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"LI2XVZPVA7EMI4Y4","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"LI2XVZPV","created_at":"2026-07-05T11:04:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LI2XVZPVA7EMI4Y4APH3TYEUCI","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18280","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T11:37:40Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"fd0f1739a5eaab9a77a620bb19a97c48544ea30e933428434c92ca0f8b602941","abstract_canon_sha256":"1fb69cd231489cb7d946e10b5908de15fd8c352491dc1189ce746107d6cd939f"},"schema_version":"1.0"},"canonical_sha256":"5a357ae5f507c8c4731c03cfb9e094123c0edd2a4acc0abe369ee87b7dcae07f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:20.941133Z","signature_b64":"XC08rxUbVjEtxS12VNo3MYLWyMnLCBQJJBzdaQgcj6SqVgB1xIsP1NTr+Kp4/FYLduhDOdrQEd/zBIGnO/FXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a357ae5f507c8c4731c03cfb9e094123c0edd2a4acc0abe369ee87b7dcae07f","last_reissued_at":"2026-07-05T11:04:20.940659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:20.940659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18280","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4ErZMtVNlfMNju5ZgLIik7lMj5KnAz6p2cJDSPdBshMT6KsMcD6e77OiczI2qXsD+NNKDD39ycMZfkU44dLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:38:32.758851Z"},"content_sha256":"5b190b063930d7a9ea9fa6eb2c5a7fd3e85937e61570550a793dad84a1041e8c","schema_version":"1.0","event_id":"sha256:5b190b063930d7a9ea9fa6eb2c5a7fd3e85937e61570550a793dad84a1041e8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LI2XVZPVA7EMI4Y4APH3TYEUCI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bo Zhang, Haoyu Liang, Jun Zhu, Youran Sun, Yunfeng Cai","submitted_at":"2025-01-30T11:37:40Z","abstract_excerpt":"The security issue of large language models (LLMs) has gained wide attention recently, with various defense mechanisms developed to prevent harmful output, among which safeguards based on text embedding models serve as a fundamental defense. Through testing, we discover that the output distribution of text embedding models is severely biased with a large mean. Inspired by this observation, we propose novel, efficient methods to search for **universal magic words** that attack text embedding models. Universal magic words as suffixes can shift the embedding of any text towards the bias direction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18280","kind":"arxiv","version":3},"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/2501.18280/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":"2026-07-05T11:04:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B+OQ74+QergbFKaR2Ysx/WOLc4J5NfrE8TlmJrz4n0D4zztXmTyv70zfcdeDasNcFlbPFtLfSCh6+FK1IhYQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:38:32.759385Z"},"content_sha256":"e25226982e79c920827bc6ee65a23f8ce76ab6a147103e0f28ecb3aba466e48f","schema_version":"1.0","event_id":"sha256:e25226982e79c920827bc6ee65a23f8ce76ab6a147103e0f28ecb3aba466e48f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LI2XVZPVA7EMI4Y4APH3TYEUCI/bundle.json","state_url":"https://pith.science/pith/LI2XVZPVA7EMI4Y4APH3TYEUCI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LI2XVZPVA7EMI4Y4APH3TYEUCI/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":"2026-08-07T11:38:32Z","links":{"resolver":"https://pith.science/pith/LI2XVZPVA7EMI4Y4APH3TYEUCI","bundle":"https://pith.science/pith/LI2XVZPVA7EMI4Y4APH3TYEUCI/bundle.json","state":"https://pith.science/pith/LI2XVZPVA7EMI4Y4APH3TYEUCI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LI2XVZPVA7EMI4Y4APH3TYEUCI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LI2XVZPVA7EMI4Y4APH3TYEUCI","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":"1fb69cd231489cb7d946e10b5908de15fd8c352491dc1189ce746107d6cd939f","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T11:37:40Z","title_canon_sha256":"fd0f1739a5eaab9a77a620bb19a97c48544ea30e933428434c92ca0f8b602941"},"schema_version":"1.0","source":{"id":"2501.18280","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18280","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18280v3","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18280","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"LI2XVZPVA7EM","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"LI2XVZPVA7EMI4Y4","created_at":"2026-07-05T11:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"LI2XVZPV","created_at":"2026-07-05T11:04:20Z"}],"graph_snapshots":[{"event_id":"sha256:e25226982e79c920827bc6ee65a23f8ce76ab6a147103e0f28ecb3aba466e48f","target":"graph","created_at":"2026-07-05T11:04:20Z","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/2501.18280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The security issue of large language models (LLMs) has gained wide attention recently, with various defense mechanisms developed to prevent harmful output, among which safeguards based on text embedding models serve as a fundamental defense. Through testing, we discover that the output distribution of text embedding models is severely biased with a large mean. Inspired by this observation, we propose novel, efficient methods to search for **universal magic words** that attack text embedding models. Universal magic words as suffixes can shift the embedding of any text towards the bias direction","authors_text":"Bo Zhang, Haoyu Liang, Jun Zhu, Youran Sun, Yunfeng Cai","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T11:37:40Z","title":"Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18280","kind":"arxiv","version":3},"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":"sha256:5b190b063930d7a9ea9fa6eb2c5a7fd3e85937e61570550a793dad84a1041e8c","target":"record","created_at":"2026-07-05T11:04:20Z","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":"1fb69cd231489cb7d946e10b5908de15fd8c352491dc1189ce746107d6cd939f","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-30T11:37:40Z","title_canon_sha256":"fd0f1739a5eaab9a77a620bb19a97c48544ea30e933428434c92ca0f8b602941"},"schema_version":"1.0","source":{"id":"2501.18280","kind":"arxiv","version":3}},"canonical_sha256":"5a357ae5f507c8c4731c03cfb9e094123c0edd2a4acc0abe369ee87b7dcae07f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a357ae5f507c8c4731c03cfb9e094123c0edd2a4acc0abe369ee87b7dcae07f","first_computed_at":"2026-07-05T11:04:20.940659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:20.940659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XC08rxUbVjEtxS12VNo3MYLWyMnLCBQJJBzdaQgcj6SqVgB1xIsP1NTr+Kp4/FYLduhDOdrQEd/zBIGnO/FXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:20.941133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18280","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b190b063930d7a9ea9fa6eb2c5a7fd3e85937e61570550a793dad84a1041e8c","sha256:e25226982e79c920827bc6ee65a23f8ce76ab6a147103e0f28ecb3aba466e48f"],"state_sha256":"288535d0f777d812bb0dbf40cd20bca7b124b3d841b0c576faa981458239041a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7M1de9lW6WqMAwRtNLLmycDEEMMPYQtC0VHxxjkOUowDVt/XWO/q6rnwBy4XL189/VLHeKVW2nR0fvSfForvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T11:38:32.764754Z","bundle_sha256":"538eb7b4c53e174e57fa0f65f510e327f0b3cb79ed5da44f2cea4032e7d3ced8"}}