{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IUJUTK3PXTV5TZBR5RAW432HST","short_pith_number":"pith:IUJUTK3P","canonical_record":{"source":{"id":"2402.13148","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T17:04:06Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"b80bbe63c9c6980b3f27fbc3f4a3c0f9361168debf58982837f3223e53e16c93","abstract_canon_sha256":"0fac502ddcf374f887f78c994b03d1d47e97241d06d34c8488ec765ce3450433"},"schema_version":"1.0"},"canonical_sha256":"451349ab6fbcebd9e431ec416e6f4794d8e418c03390b96cec1a7e303c17dd7d","source":{"kind":"arxiv","id":"2402.13148","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13148","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13148v3","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13148","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"pith_short_12","alias_value":"IUJUTK3PXTV5","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"pith_short_16","alias_value":"IUJUTK3PXTV5TZBR","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"pith_short_8","alias_value":"IUJUTK3P","created_at":"2026-07-05T10:18:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IUJUTK3PXTV5TZBR5RAW432HST","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13148","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T17:04:06Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"b80bbe63c9c6980b3f27fbc3f4a3c0f9361168debf58982837f3223e53e16c93","abstract_canon_sha256":"0fac502ddcf374f887f78c994b03d1d47e97241d06d34c8488ec765ce3450433"},"schema_version":"1.0"},"canonical_sha256":"451349ab6fbcebd9e431ec416e6f4794d8e418c03390b96cec1a7e303c17dd7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:07.806253Z","signature_b64":"UXGBBTPSYj1d1PvjC2fDB4dFn+TyjAHu1LVMvldjK7K4eNOy+4e6KKApSugdrmpJTgdRViZ3O+zalT2u6kjTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"451349ab6fbcebd9e431ec416e6f4794d8e418c03390b96cec1a7e303c17dd7d","last_reissued_at":"2026-07-05T10:18:07.805826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:07.805826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13148","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":"2026-07-05T10:18:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5daSqqCuhRFR+n7biwkmkWutbf7U41PQJH4oViGPMr8XsnVgtWysDidJzDRUiBBe+Nj3HHnpeBBlU9UVQHhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:08:45.894115Z"},"content_sha256":"627eee8ff35e8d93fdcb5f32ae1a815fca687e9133f2daeec0a876eae60672f1","schema_version":"1.0","event_id":"sha256:627eee8ff35e8d93fdcb5f32ae1a815fca687e9133f2daeec0a876eae60672f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IUJUTK3PXTV5TZBR5RAW432HST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Defending Jailbreak Prompts via In-Context Adversarial Game","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Haomin Zhuang, Hongyan Bao, Kehan Guo, Xiangliang Zhang, Yufei Han, Yujun Zhou, Zhenwen Liang","submitted_at":"2024-02-20T17:04:06Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications. However, concerns regarding their security, particularly the vulnerability to jailbreak attacks, persist. Drawing inspiration from adversarial training in deep learning and LLM agent learning processes, we introduce the In-Context Adversarial Game (ICAG) for defending against jailbreaks without the need for fine-tuning. ICAG leverages agent learning to conduct an adversarial game, aiming to dynamically extend knowledge to defend against jailbreaks. Unlike traditional methods that rely on static datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13148","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/2402.13148/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":"2026-07-05T10:18:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KXrGzj/PuAXGzWggjXf5YYhRr1+Yn2lgmg8WkGoj2j8vUFsS/sXkyQ12zVearsPLMAo4SbTbe0Yre/6LaHOPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:08:45.895049Z"},"content_sha256":"6f50874305bd458d8946cb2eb6a3f4e5c1441c7a57f89f85a0a01b4a26f55384","schema_version":"1.0","event_id":"sha256:6f50874305bd458d8946cb2eb6a3f4e5c1441c7a57f89f85a0a01b4a26f55384"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUJUTK3PXTV5TZBR5RAW432HST/bundle.json","state_url":"https://pith.science/pith/IUJUTK3PXTV5TZBR5RAW432HST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUJUTK3PXTV5TZBR5RAW432HST/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":"2026-08-05T05:08:45Z","links":{"resolver":"https://pith.science/pith/IUJUTK3PXTV5TZBR5RAW432HST","bundle":"https://pith.science/pith/IUJUTK3PXTV5TZBR5RAW432HST/bundle.json","state":"https://pith.science/pith/IUJUTK3PXTV5TZBR5RAW432HST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUJUTK3PXTV5TZBR5RAW432HST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IUJUTK3PXTV5TZBR5RAW432HST","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":"0fac502ddcf374f887f78c994b03d1d47e97241d06d34c8488ec765ce3450433","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T17:04:06Z","title_canon_sha256":"b80bbe63c9c6980b3f27fbc3f4a3c0f9361168debf58982837f3223e53e16c93"},"schema_version":"1.0","source":{"id":"2402.13148","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13148","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13148v3","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13148","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"pith_short_12","alias_value":"IUJUTK3PXTV5","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"pith_short_16","alias_value":"IUJUTK3PXTV5TZBR","created_at":"2026-07-05T10:18:07Z"},{"alias_kind":"pith_short_8","alias_value":"IUJUTK3P","created_at":"2026-07-05T10:18:07Z"}],"graph_snapshots":[{"event_id":"sha256:6f50874305bd458d8946cb2eb6a3f4e5c1441c7a57f89f85a0a01b4a26f55384","target":"graph","created_at":"2026-07-05T10:18:07Z","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/2402.13148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications. However, concerns regarding their security, particularly the vulnerability to jailbreak attacks, persist. Drawing inspiration from adversarial training in deep learning and LLM agent learning processes, we introduce the In-Context Adversarial Game (ICAG) for defending against jailbreaks without the need for fine-tuning. ICAG leverages agent learning to conduct an adversarial game, aiming to dynamically extend knowledge to defend against jailbreaks. Unlike traditional methods that rely on static datase","authors_text":"Haomin Zhuang, Hongyan Bao, Kehan Guo, Xiangliang Zhang, Yufei Han, Yujun Zhou, Zhenwen Liang","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T17:04:06Z","title":"Defending Jailbreak Prompts via In-Context Adversarial Game"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13148","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":"sha256:627eee8ff35e8d93fdcb5f32ae1a815fca687e9133f2daeec0a876eae60672f1","target":"record","created_at":"2026-07-05T10:18:07Z","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":"0fac502ddcf374f887f78c994b03d1d47e97241d06d34c8488ec765ce3450433","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T17:04:06Z","title_canon_sha256":"b80bbe63c9c6980b3f27fbc3f4a3c0f9361168debf58982837f3223e53e16c93"},"schema_version":"1.0","source":{"id":"2402.13148","kind":"arxiv","version":3}},"canonical_sha256":"451349ab6fbcebd9e431ec416e6f4794d8e418c03390b96cec1a7e303c17dd7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"451349ab6fbcebd9e431ec416e6f4794d8e418c03390b96cec1a7e303c17dd7d","first_computed_at":"2026-07-05T10:18:07.805826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:07.805826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UXGBBTPSYj1d1PvjC2fDB4dFn+TyjAHu1LVMvldjK7K4eNOy+4e6KKApSugdrmpJTgdRViZ3O+zalT2u6kjTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:07.806253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13148","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:627eee8ff35e8d93fdcb5f32ae1a815fca687e9133f2daeec0a876eae60672f1","sha256:6f50874305bd458d8946cb2eb6a3f4e5c1441c7a57f89f85a0a01b4a26f55384"],"state_sha256":"43fa11850bc767694a43bdfc83652ae13adbc282be20353227f7c86083126345"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qyGzVT/YEVTcQycIL6rxUKydZwFCAVnnQ1UdtHqqMFMZnottbsCZSXlzjw5lqzCzjImAktATOM8N9yd6M1rWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:08:45.901332Z","bundle_sha256":"4fa872c4b731cc8d0fc80fba6234440bb3af86c54f06ede2d0f47ee7ecd88807"}}