{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPCVHXTSGFIHOWNHCU42GK3TLN","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":"1d496de25e9657eb09b9fba4436c40fbe2e55d4a6dce7b9618c0f19a08271259","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-12-07T20:09:01Z","title_canon_sha256":"d13cddfb591e1f204d00a1fc38281247a4ea08c2523d1d758e0d6948d2d678d9"},"schema_version":"1.0","source":{"id":"2412.05734","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05734","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05734v2","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05734","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"pith_short_12","alias_value":"RPCVHXTSGFIH","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"pith_short_16","alias_value":"RPCVHXTSGFIHOWNH","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"pith_short_8","alias_value":"RPCVHXTS","created_at":"2026-07-05T11:50:29Z"}],"graph_snapshots":[{"event_id":"sha256:183248d1f03d35a2d30ada44b6e3bd85fa30e8821094c6f7dc6b747385d7de0d","target":"graph","created_at":"2026-07-05T11:50:29Z","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/2412.05734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have discovered that large language models (LLM) may be ``fooled'' to output private information, including training data, system prompts, and personally identifiable information, under carefully crafted adversarial prompts. Existing red-teaming approaches for privacy leakage either rely on manual efforts or focus solely on system prompt extraction, making them ineffective for severe risks of training data leakage. We propose LeakAgent, a novel black-box red-teaming framework for LLM privacy leakage. Our framework trains an open-source LLM through reinforcement learning as the a","authors_text":"Dawn Song, Wenbo Guo, Xian Wu, Xuandong Zhao, Ye Yu, Yuzhou Nie, Zhun Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-12-07T20:09:01Z","title":"LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05734","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":"sha256:1a5144858a6c66db6fe6eaa171f6e8ad0420741713dd8764ea73430fc564bfd1","target":"record","created_at":"2026-07-05T11:50:29Z","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":"1d496de25e9657eb09b9fba4436c40fbe2e55d4a6dce7b9618c0f19a08271259","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-12-07T20:09:01Z","title_canon_sha256":"d13cddfb591e1f204d00a1fc38281247a4ea08c2523d1d758e0d6948d2d678d9"},"schema_version":"1.0","source":{"id":"2412.05734","kind":"arxiv","version":2}},"canonical_sha256":"8bc553de7231507759a71539a32b735b5d72f0775ca210e9ebdbbb90ad1e0522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bc553de7231507759a71539a32b735b5d72f0775ca210e9ebdbbb90ad1e0522","first_computed_at":"2026-07-05T11:50:29.344419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:29.344419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rm04PO9LRR2efXo+IEcPEfH1AmwCSrHejYY4f2YH+Hc4P6NIhjkp6KDXlWMrelfVK8sYkoTHmw8zB6XI8w15DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:29.344908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05734","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a5144858a6c66db6fe6eaa171f6e8ad0420741713dd8764ea73430fc564bfd1","sha256:183248d1f03d35a2d30ada44b6e3bd85fa30e8821094c6f7dc6b747385d7de0d"],"state_sha256":"9efb8e2ab548d2ed82d35bcb122d0f1259ca78143da8a1eb3e12e483f9015049"}