{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ROXJKU2B7PNDUAI6DXV77WHLMT","short_pith_number":"pith:ROXJKU2B","canonical_record":{"source":{"id":"2410.01438","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T11:40:49Z","cross_cats_sorted":[],"title_canon_sha256":"fecd5d4d1e5220f38b4074d6122e3ad92fa6461795df7d43a23f740a4d9a2b2c","abstract_canon_sha256":"0d871d66dcadae12d66a028aa0730147239978854aa3249c0eaadfce3eb84be6"},"schema_version":"1.0"},"canonical_sha256":"8bae955341fbda3a011e1debffd8eb64e2b7503d64465fc2145347c44579c731","source":{"kind":"arxiv","id":"2410.01438","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01438","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01438v2","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01438","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_12","alias_value":"ROXJKU2B7PND","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_16","alias_value":"ROXJKU2B7PNDUAI6","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_8","alias_value":"ROXJKU2B","created_at":"2026-07-05T10:08:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ROXJKU2B7PNDUAI6DXV77WHLMT","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01438","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T11:40:49Z","cross_cats_sorted":[],"title_canon_sha256":"fecd5d4d1e5220f38b4074d6122e3ad92fa6461795df7d43a23f740a4d9a2b2c","abstract_canon_sha256":"0d871d66dcadae12d66a028aa0730147239978854aa3249c0eaadfce3eb84be6"},"schema_version":"1.0"},"canonical_sha256":"8bae955341fbda3a011e1debffd8eb64e2b7503d64465fc2145347c44579c731","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:22.137864Z","signature_b64":"jsJJ5PRorLQ71nlZBNqjfUVp2d8AIc3GL3NgK6pjaWp8kU9zhoYP7d0rPyD3pl0e/pdba2fcSOCtyLGIXjbdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bae955341fbda3a011e1debffd8eb64e2b7503d64465fc2145347c44579c731","last_reissued_at":"2026-07-05T10:08:22.137470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:22.137470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01438","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:08:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DXE3nzBAdA9o6v6TKZQhCmDBV8iX3VgWusysyEz0xOQGfv4UNPx5k6ZyJxgfq0GFw4naAZEa871qm8LiR/+XCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:19:27.804545Z"},"content_sha256":"0bede2453c19afb511798163ffe8d2ce06b921561f1f75916ce278a2b9e1254c","schema_version":"1.0","event_id":"sha256:0bede2453c19afb511798163ffe8d2ce06b921561f1f75916ce278a2b9e1254c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ROXJKU2B7PNDUAI6DXV77WHLMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chia-Mu Yu, Ching-Chia Kao, Chun-Shien Lu, Chu-Song Chen","submitted_at":"2024-10-02T11:40:49Z","abstract_excerpt":"Vision-Language Models (VLMs) have achieved remarkable performance on a variety of tasks, yet they remain vulnerable to jailbreak attacks that compromise safety and reliability. In this paper, we provide an information-theoretic framework for understanding the fundamental trade-off between the effectiveness of these attacks and their stealthiness. Drawing on Fano's inequality, we demonstrate how an attacker's success probability is intrinsically linked to the stealthiness of generated prompts. Building on this, we propose an efficient algorithm for detecting non-stealthy jailbreak attacks, off"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01438","kind":"arxiv","version":2},"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/2410.01438/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":"2026-07-05T10:08:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BES5/lIjxAjUaphBhBujEkWyLqb2WAWoWe97j9iL2qFxyHPa7kyq6eP7OeEpV1sCqLIKfPKBilAPWMk6bIfxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:19:27.805045Z"},"content_sha256":"223427691b789c012e4f0829e8c03d741f7cddb51bcafd601814c520030f62a1","schema_version":"1.0","event_id":"sha256:223427691b789c012e4f0829e8c03d741f7cddb51bcafd601814c520030f62a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ROXJKU2B7PNDUAI6DXV77WHLMT/bundle.json","state_url":"https://pith.science/pith/ROXJKU2B7PNDUAI6DXV77WHLMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ROXJKU2B7PNDUAI6DXV77WHLMT/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":"2026-08-06T06:19:27Z","links":{"resolver":"https://pith.science/pith/ROXJKU2B7PNDUAI6DXV77WHLMT","bundle":"https://pith.science/pith/ROXJKU2B7PNDUAI6DXV77WHLMT/bundle.json","state":"https://pith.science/pith/ROXJKU2B7PNDUAI6DXV77WHLMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ROXJKU2B7PNDUAI6DXV77WHLMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ROXJKU2B7PNDUAI6DXV77WHLMT","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":"0d871d66dcadae12d66a028aa0730147239978854aa3249c0eaadfce3eb84be6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T11:40:49Z","title_canon_sha256":"fecd5d4d1e5220f38b4074d6122e3ad92fa6461795df7d43a23f740a4d9a2b2c"},"schema_version":"1.0","source":{"id":"2410.01438","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01438","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01438v2","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01438","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_12","alias_value":"ROXJKU2B7PND","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_16","alias_value":"ROXJKU2B7PNDUAI6","created_at":"2026-07-05T10:08:22Z"},{"alias_kind":"pith_short_8","alias_value":"ROXJKU2B","created_at":"2026-07-05T10:08:22Z"}],"graph_snapshots":[{"event_id":"sha256:223427691b789c012e4f0829e8c03d741f7cddb51bcafd601814c520030f62a1","target":"graph","created_at":"2026-07-05T10:08:22Z","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/2410.01438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have achieved remarkable performance on a variety of tasks, yet they remain vulnerable to jailbreak attacks that compromise safety and reliability. In this paper, we provide an information-theoretic framework for understanding the fundamental trade-off between the effectiveness of these attacks and their stealthiness. Drawing on Fano's inequality, we demonstrate how an attacker's success probability is intrinsically linked to the stealthiness of generated prompts. Building on this, we propose an efficient algorithm for detecting non-stealthy jailbreak attacks, off","authors_text":"Chia-Mu Yu, Ching-Chia Kao, Chun-Shien Lu, Chu-Song Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T11:40:49Z","title":"The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01438","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":"sha256:0bede2453c19afb511798163ffe8d2ce06b921561f1f75916ce278a2b9e1254c","target":"record","created_at":"2026-07-05T10:08:22Z","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":"0d871d66dcadae12d66a028aa0730147239978854aa3249c0eaadfce3eb84be6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T11:40:49Z","title_canon_sha256":"fecd5d4d1e5220f38b4074d6122e3ad92fa6461795df7d43a23f740a4d9a2b2c"},"schema_version":"1.0","source":{"id":"2410.01438","kind":"arxiv","version":2}},"canonical_sha256":"8bae955341fbda3a011e1debffd8eb64e2b7503d64465fc2145347c44579c731","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bae955341fbda3a011e1debffd8eb64e2b7503d64465fc2145347c44579c731","first_computed_at":"2026-07-05T10:08:22.137470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:22.137470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jsJJ5PRorLQ71nlZBNqjfUVp2d8AIc3GL3NgK6pjaWp8kU9zhoYP7d0rPyD3pl0e/pdba2fcSOCtyLGIXjbdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:22.137864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01438","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bede2453c19afb511798163ffe8d2ce06b921561f1f75916ce278a2b9e1254c","sha256:223427691b789c012e4f0829e8c03d741f7cddb51bcafd601814c520030f62a1"],"state_sha256":"ad08d1eac0d70b8e2f4713edcab9b30044f8c1205808f7ef47952fe35c0de845"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j1hfueXC4C6O/JcoYziut2mtKBJxdN5KH1asfFgWi+gNuHyOHo+LI0ZCBwB5jmcpQRKlNNw7M4hR02QnMTBWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:19:27.808644Z","bundle_sha256":"a11e4bc5f244744468908d5f2cf17825431185aeb202c4c1ee934576d42c8e50"}}