{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NDTH47HYNQYXOPON2YMP4XATMY","short_pith_number":"pith:NDTH47HY","schema_version":"1.0","canonical_sha256":"68e67e7cf86c31773dcdd618fe5c136638ac876aaeb5f7c09c6bb9ec8674dd04","source":{"kind":"arxiv","id":"2506.07402","version":1},"attestation_state":"computed","paper":{"title":"Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Sibei Yang, Wenjie Wang, Yukai Zhou","submitted_at":"2025-06-09T03:52:43Z","abstract_excerpt":"Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly answering harmless-looking inputs can be dangerous and cause real-world harm (Implicit Harm). We systematically reformulate the LLM risk landscape through a structured quadrant perspective based on output factuality and input harmlessness, uncovering an overlooked high-risk region. To investigate this gap, we propose JailFlipBench, a benchmark aims to capture"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.07402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-09T03:52:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f3d54bc2fa964961b042f2dd685b1920e0830cd1130096644b4c9a0b4b9a78f6","abstract_canon_sha256":"b6bf14002cdfefede20958b9caf6179a60b2ab072ed923971ecd46f2b88e3b6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:26.643310Z","signature_b64":"sel9cL3kgnh5QD9NP1IM886rw4G1DZrGSTBDhZTpeM6R2LG/bPH6zpgCIIEhwVHPasg/+yyilTHbFd/W6OwlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68e67e7cf86c31773dcdd618fe5c136638ac876aaeb5f7c09c6bb9ec8674dd04","last_reissued_at":"2026-07-05T11:18:26.642854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:26.642854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Sibei Yang, Wenjie Wang, Yukai Zhou","submitted_at":"2025-06-09T03:52:43Z","abstract_excerpt":"Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly answering harmless-looking inputs can be dangerous and cause real-world harm (Implicit Harm). We systematically reformulate the LLM risk landscape through a structured quadrant perspective based on output factuality and input harmlessness, uncovering an overlooked high-risk region. To investigate this gap, we propose JailFlipBench, a benchmark aims to capture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07402","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/2506.07402/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.07402","created_at":"2026-07-05T11:18:26.642915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07402v1","created_at":"2026-07-05T11:18:26.642915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07402","created_at":"2026-07-05T11:18:26.642915+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDTH47HYNQYX","created_at":"2026-07-05T11:18:26.642915+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDTH47HYNQYXOPON","created_at":"2026-07-05T11:18:26.642915+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDTH47HY","created_at":"2026-07-05T11:18:26.642915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY","json":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY.json","graph_json":"https://pith.science/api/pith-number/NDTH47HYNQYXOPON2YMP4XATMY/graph.json","events_json":"https://pith.science/api/pith-number/NDTH47HYNQYXOPON2YMP4XATMY/events.json","paper":"https://pith.science/paper/NDTH47HY"},"agent_actions":{"view_html":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY","download_json":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY.json","view_paper":"https://pith.science/paper/NDTH47HY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07402&json=true","fetch_graph":"https://pith.science/api/pith-number/NDTH47HYNQYXOPON2YMP4XATMY/graph.json","fetch_events":"https://pith.science/api/pith-number/NDTH47HYNQYXOPON2YMP4XATMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY/action/storage_attestation","attest_author":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY/action/author_attestation","sign_citation":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY/action/citation_signature","submit_replication":"https://pith.science/pith/NDTH47HYNQYXOPON2YMP4XATMY/action/replication_record"}},"created_at":"2026-07-05T11:18:26.642915+00:00","updated_at":"2026-07-05T11:18:26.642915+00:00"}