{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y2HMAYVSQF7CXCBQEAGXFOEWEZ","short_pith_number":"pith:Y2HMAYVS","canonical_record":{"source":{"id":"2412.12621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:33:41Z","cross_cats_sorted":[],"title_canon_sha256":"c21d2c06c65191e8d075bf8b54e006ec94c55a818ede1da75370a32748e2c2b5","abstract_canon_sha256":"7494b76d797cebbfe386eba2af375a50a3809ea2461cc06169a98c55b8886ed1"},"schema_version":"1.0"},"canonical_sha256":"c68ec062b2817e2b8830200d72b896267a0eccccbc4b3973a1c02a67277f5f1b","source":{"kind":"arxiv","id":"2412.12621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12621","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12621v1","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12621","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"Y2HMAYVSQF7C","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"Y2HMAYVSQF7CXCBQ","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"Y2HMAYVS","created_at":"2026-07-05T09:50:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y2HMAYVSQF7CXCBQEAGXFOEWEZ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:33:41Z","cross_cats_sorted":[],"title_canon_sha256":"c21d2c06c65191e8d075bf8b54e006ec94c55a818ede1da75370a32748e2c2b5","abstract_canon_sha256":"7494b76d797cebbfe386eba2af375a50a3809ea2461cc06169a98c55b8886ed1"},"schema_version":"1.0"},"canonical_sha256":"c68ec062b2817e2b8830200d72b896267a0eccccbc4b3973a1c02a67277f5f1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:18.079702Z","signature_b64":"bSytQzY4f9+1DmNmOXeXYbCRbTbqq4oGoAHSQYGXYXftJJE5RkR9GGaMH3TG7Yw+QYf/z+D5TtoWxL34sIrLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c68ec062b2817e2b8830200d72b896267a0eccccbc4b3973a1c02a67277f5f1b","last_reissued_at":"2026-07-05T09:50:18.079120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:18.079120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12621","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lGzBZDeuDi5mkxiJuDRVisuwEX40Q8zuLC7y6+CKKnuqrkYGGhZW3N1w/rSQ5En+vf4ISDZMAOGUrVQCqolAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:12:09.760948Z"},"content_sha256":"bcf854bdfb2575c78a6bf499640a78213330b9feba3c29407f12eee6e85db509","schema_version":"1.0","event_id":"sha256:bcf854bdfb2575c78a6bf499640a78213330b9feba3c29407f12eee6e85db509"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y2HMAYVSQF7CXCBQEAGXFOEWEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jailbreaking? One Step Is Enough!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aimin Yang, Hongyan Wu, Junhao Chen, Nankai Lin, Peijian Zeng, Weixiong Zheng, Yiwei Li, Yongmei Zhou","submitted_at":"2024-12-17T07:33:41Z","abstract_excerpt":"Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However, current jailbreak methods and the target model's defenses are engaged in an independent and adversarial process, resulting in the need for frequent attack iterations and redesigning attacks for different models. To address these gaps, we propose a Reverse Embedded Defense Attack (REDA) mechanism that disguises the attack intention as the \"defense\". intention "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12621","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/2412.12621/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":"2026-07-05T09:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCQHyuuba2+SvrxMYni9A72k2yhDugEBCISQEEDbhCZzeCDlJRP/88Jun2aPizEaU3R8eLmPkxjewV/KIV3YAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:12:09.761767Z"},"content_sha256":"92d48f2bbd66ba9d3495a36c49c3c49012eaff1137d87d932d85a62bf38d78ba","schema_version":"1.0","event_id":"sha256:92d48f2bbd66ba9d3495a36c49c3c49012eaff1137d87d932d85a62bf38d78ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y2HMAYVSQF7CXCBQEAGXFOEWEZ/bundle.json","state_url":"https://pith.science/pith/Y2HMAYVSQF7CXCBQEAGXFOEWEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y2HMAYVSQF7CXCBQEAGXFOEWEZ/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":"2026-08-11T09:12:09Z","links":{"resolver":"https://pith.science/pith/Y2HMAYVSQF7CXCBQEAGXFOEWEZ","bundle":"https://pith.science/pith/Y2HMAYVSQF7CXCBQEAGXFOEWEZ/bundle.json","state":"https://pith.science/pith/Y2HMAYVSQF7CXCBQEAGXFOEWEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y2HMAYVSQF7CXCBQEAGXFOEWEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y2HMAYVSQF7CXCBQEAGXFOEWEZ","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":"7494b76d797cebbfe386eba2af375a50a3809ea2461cc06169a98c55b8886ed1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:33:41Z","title_canon_sha256":"c21d2c06c65191e8d075bf8b54e006ec94c55a818ede1da75370a32748e2c2b5"},"schema_version":"1.0","source":{"id":"2412.12621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12621","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12621v1","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12621","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"Y2HMAYVSQF7C","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"Y2HMAYVSQF7CXCBQ","created_at":"2026-07-05T09:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"Y2HMAYVS","created_at":"2026-07-05T09:50:18Z"}],"graph_snapshots":[{"event_id":"sha256:92d48f2bbd66ba9d3495a36c49c3c49012eaff1137d87d932d85a62bf38d78ba","target":"graph","created_at":"2026-07-05T09:50:18Z","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/2412.12621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However, current jailbreak methods and the target model's defenses are engaged in an independent and adversarial process, resulting in the need for frequent attack iterations and redesigning attacks for different models. To address these gaps, we propose a Reverse Embedded Defense Attack (REDA) mechanism that disguises the attack intention as the \"defense\". intention ","authors_text":"Aimin Yang, Hongyan Wu, Junhao Chen, Nankai Lin, Peijian Zeng, Weixiong Zheng, Yiwei Li, Yongmei Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:33:41Z","title":"Jailbreaking? One Step Is Enough!"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12621","kind":"arxiv","version":1},"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:bcf854bdfb2575c78a6bf499640a78213330b9feba3c29407f12eee6e85db509","target":"record","created_at":"2026-07-05T09:50:18Z","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":"7494b76d797cebbfe386eba2af375a50a3809ea2461cc06169a98c55b8886ed1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:33:41Z","title_canon_sha256":"c21d2c06c65191e8d075bf8b54e006ec94c55a818ede1da75370a32748e2c2b5"},"schema_version":"1.0","source":{"id":"2412.12621","kind":"arxiv","version":1}},"canonical_sha256":"c68ec062b2817e2b8830200d72b896267a0eccccbc4b3973a1c02a67277f5f1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c68ec062b2817e2b8830200d72b896267a0eccccbc4b3973a1c02a67277f5f1b","first_computed_at":"2026-07-05T09:50:18.079120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:18.079120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bSytQzY4f9+1DmNmOXeXYbCRbTbqq4oGoAHSQYGXYXftJJE5RkR9GGaMH3TG7Yw+QYf/z+D5TtoWxL34sIrLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:18.079702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcf854bdfb2575c78a6bf499640a78213330b9feba3c29407f12eee6e85db509","sha256:92d48f2bbd66ba9d3495a36c49c3c49012eaff1137d87d932d85a62bf38d78ba"],"state_sha256":"27da3cb7c17c56789ddcdd210dbb2ce4cc1f141278027d332f83b019b670bfc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9orjz46P/Qh56WyLhvoBnPPESWsO6AQ9FggVSNxT9Yco+Vx4ogVuRMB9b0EPCve5uTKP8OuEqBkXgnCPUFuoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T09:12:09.767701Z","bundle_sha256":"fff754939b078d032c5bfacc2705cbfdb10a7ca9037a972c94e85aafb464c516"}}