{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MO2AEVWG7VLD3KHS6MO6QSOJ65","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":"b8ff1f647133c988c95887e317daa3ecda5086041fb628ea86fe119dfec57499","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:47:32Z","title_canon_sha256":"390b8eb03853a5416533e3651c89ecb4724480dc13db7d9a7d43c68a8cb494eb"},"schema_version":"1.0","source":{"id":"2505.18556","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18556","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18556v2","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18556","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"MO2AEVWG7VLD","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"pith_short_16","alias_value":"MO2AEVWG7VLD3KHS","created_at":"2026-07-05T11:58:29Z"},{"alias_kind":"pith_short_8","alias_value":"MO2AEVWG","created_at":"2026-07-05T11:58:29Z"}],"graph_snapshots":[{"event_id":"sha256:1f26f94389dc801b125b45557b7cb19719b96b9dd4267149f1b3ba59a2387bbc","target":"graph","created_at":"2026-07-05T11:58:29Z","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/2505.18556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation guardrails, showing a significant success against content-level jailbreaks, the robustness of these intent-aware guardrails under malicious manipulations remains under-explored. In this work, we investigate the vulnerability of intent-aware guardrails and demonstrate that LLMs exhibit implicit intent detection capabilities. We propose a two-stage intent-based ","authors_text":"Gaby G. Dagher, Haibo Jin, Haohan Wang, Jun Zhuang, Wenbin Zhang, Ye Zhang, Zhengjian Kang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:47:32Z","title":"Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18556","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:e336ebe57c33c96739b568fc38eed339c675db159fd30a2f719142db95495b7a","target":"record","created_at":"2026-07-05T11:58:29Z","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":"b8ff1f647133c988c95887e317daa3ecda5086041fb628ea86fe119dfec57499","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:47:32Z","title_canon_sha256":"390b8eb03853a5416533e3651c89ecb4724480dc13db7d9a7d43c68a8cb494eb"},"schema_version":"1.0","source":{"id":"2505.18556","kind":"arxiv","version":2}},"canonical_sha256":"63b40256c6fd563da8f2f31de849c9f76852ff83a044535d7e688eb16082bb85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63b40256c6fd563da8f2f31de849c9f76852ff83a044535d7e688eb16082bb85","first_computed_at":"2026-07-05T11:58:29.745694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:29.745694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"elUeJUE28k1Ts9ZAPZArWMLbj96LU216Kk1APLsWrcvV/HtYe/zAf10Mgu0i4Pw4MpxVZZ8WzBx4IoGHGA9cDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:29.746210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18556","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e336ebe57c33c96739b568fc38eed339c675db159fd30a2f719142db95495b7a","sha256:1f26f94389dc801b125b45557b7cb19719b96b9dd4267149f1b3ba59a2387bbc"],"state_sha256":"b429ad2931fce88ad6c88fdff81578450a0314373414fde94fe2cc54f0a8a73c"}