{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:27WJKKTCNWBWI4BQMZRDZJEG3I","short_pith_number":"pith:27WJKKTC","canonical_record":{"source":{"id":"2310.12505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:15:05Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"2f6b9f8413b22a4226e5f0b9182b68432b4c63fe4e4b4c3a7f36917edfc2c421","abstract_canon_sha256":"3d0f46a6cf956b26ff472d1d5a6aea8228bfef58ee077c674dc4c2d834381034"},"schema_version":"1.0"},"canonical_sha256":"d7ec952a626d8364703066623ca486da24ca2a70958d743ded30d80757511e2f","source":{"kind":"arxiv","id":"2310.12505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12505","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12505v1","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12505","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"27WJKKTCNWBW","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"27WJKKTCNWBWI4BQ","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"27WJKKTC","created_at":"2026-07-05T07:02:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:27WJKKTCNWBWI4BQMZRDZJEG3I","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:15:05Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"2f6b9f8413b22a4226e5f0b9182b68432b4c63fe4e4b4c3a7f36917edfc2c421","abstract_canon_sha256":"3d0f46a6cf956b26ff472d1d5a6aea8228bfef58ee077c674dc4c2d834381034"},"schema_version":"1.0"},"canonical_sha256":"d7ec952a626d8364703066623ca486da24ca2a70958d743ded30d80757511e2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:39.151708Z","signature_b64":"gKePkdi14u27fQ0AFszTdgWpJOcnPMEpMsd2exzBoBl43XZQCSp6vHYiAOTWvEYLD74qaLw2bQScIZvarfRIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7ec952a626d8364703066623ca486da24ca2a70958d743ded30d80757511e2f","last_reissued_at":"2026-07-05T07:02:39.151241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:39.151241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12505","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":"2026-07-05T07:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGjltKhRSF1rm9gzuJx3mA0ham8ji27g3jJcC/qo91Rd64HhEPK7gjkcBH5hpGC/ee4bGY/YrORial1l3zYqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:26:54.550430Z"},"content_sha256":"c2702c13e33b91084b872fe67e2bc67ce2b256648f28d28dd3a799b51fc51d2f","schema_version":"1.0","event_id":"sha256:c2702c13e33b91084b872fe67e2bc67ce2b256648f28d28dd3a799b51fc51d2f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:27WJKKTCNWBWI4BQMZRDZJEG3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Boyi Deng, Fuli Feng, Qifan Wang, Wenjie Wang, Xiangnan He, Yang Deng","submitted_at":"2023-10-19T06:15:05Z","abstract_excerpt":"Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on construction cost and quality. To address these issues, we propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts. Specifically, considering the impressive capabilities of newly emerged LLMs, we propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12505","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/2310.12505/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":"2026-07-05T07:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JOum5gPVf4GlCA6YGeC1iVmyOJfSu8KeeSibZy+QgX0LZ6x89hudlYx7epTRLZgNyq5ugu1ForXF+5SEfMA6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:26:54.550947Z"},"content_sha256":"259b87e7a477245fdc1ab9b3c869f0ce927a76c93d74f8ff85376209efb8ed94","schema_version":"1.0","event_id":"sha256:259b87e7a477245fdc1ab9b3c869f0ce927a76c93d74f8ff85376209efb8ed94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/27WJKKTCNWBWI4BQMZRDZJEG3I/bundle.json","state_url":"https://pith.science/pith/27WJKKTCNWBWI4BQMZRDZJEG3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/27WJKKTCNWBWI4BQMZRDZJEG3I/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":"2026-08-09T17:26:54Z","links":{"resolver":"https://pith.science/pith/27WJKKTCNWBWI4BQMZRDZJEG3I","bundle":"https://pith.science/pith/27WJKKTCNWBWI4BQMZRDZJEG3I/bundle.json","state":"https://pith.science/pith/27WJKKTCNWBWI4BQMZRDZJEG3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/27WJKKTCNWBWI4BQMZRDZJEG3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:27WJKKTCNWBWI4BQMZRDZJEG3I","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":"3d0f46a6cf956b26ff472d1d5a6aea8228bfef58ee077c674dc4c2d834381034","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:15:05Z","title_canon_sha256":"2f6b9f8413b22a4226e5f0b9182b68432b4c63fe4e4b4c3a7f36917edfc2c421"},"schema_version":"1.0","source":{"id":"2310.12505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12505","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12505v1","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12505","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"27WJKKTCNWBW","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"27WJKKTCNWBWI4BQ","created_at":"2026-07-05T07:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"27WJKKTC","created_at":"2026-07-05T07:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:259b87e7a477245fdc1ab9b3c869f0ce927a76c93d74f8ff85376209efb8ed94","target":"graph","created_at":"2026-07-05T07:02:39Z","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/2310.12505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on construction cost and quality. To address these issues, we propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts. Specifically, considering the impressive capabilities of newly emerged LLMs, we propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context lea","authors_text":"Boyi Deng, Fuli Feng, Qifan Wang, Wenjie Wang, Xiangnan He, Yang Deng","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:15:05Z","title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12505","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:c2702c13e33b91084b872fe67e2bc67ce2b256648f28d28dd3a799b51fc51d2f","target":"record","created_at":"2026-07-05T07:02:39Z","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":"3d0f46a6cf956b26ff472d1d5a6aea8228bfef58ee077c674dc4c2d834381034","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T06:15:05Z","title_canon_sha256":"2f6b9f8413b22a4226e5f0b9182b68432b4c63fe4e4b4c3a7f36917edfc2c421"},"schema_version":"1.0","source":{"id":"2310.12505","kind":"arxiv","version":1}},"canonical_sha256":"d7ec952a626d8364703066623ca486da24ca2a70958d743ded30d80757511e2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7ec952a626d8364703066623ca486da24ca2a70958d743ded30d80757511e2f","first_computed_at":"2026-07-05T07:02:39.151241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:39.151241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gKePkdi14u27fQ0AFszTdgWpJOcnPMEpMsd2exzBoBl43XZQCSp6vHYiAOTWvEYLD74qaLw2bQScIZvarfRIDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:39.151708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2702c13e33b91084b872fe67e2bc67ce2b256648f28d28dd3a799b51fc51d2f","sha256:259b87e7a477245fdc1ab9b3c869f0ce927a76c93d74f8ff85376209efb8ed94"],"state_sha256":"7d6da890135779f1835cf9b0c396b7ed125f939d7b4e3fa605187104f5e12110"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GYPA51EWwAcEdQUZyVKbBgjsfW9itHCQ7ishrbvdsdNKuayAKbJ1HmUI7XhEjqY0AMk4SMXnephzZ8UbxQU2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:26:54.558131Z","bundle_sha256":"b828e336e25066c41488d8762e8891fd176a5c049c72567b356a12e02beef811"}}