{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AHJ2DZF3OI475A57KFC6ZKWXBN","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":"e0aad4ab7e3496512b5b4e7c2bd915706caed7d65d0ece37a9134fdc5c8e1c0f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-28T14:53:27Z","title_canon_sha256":"03119461083e3a5030c7a2bb03895acb4c628f3bb0507114b1a0ed3193757b26"},"schema_version":"1.0","source":{"id":"2605.30031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30031","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30031v1","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30031","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"AHJ2DZF3OI47","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"AHJ2DZF3OI475A57","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"AHJ2DZF3","created_at":"2026-05-29T02:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:64875ff843f251236c99cb9aae2f6216200b97e9f816d14c75f2d16edb8d8277","target":"graph","created_at":"2026-05-29T02:06:07Z","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/2605.30031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where unsafe behavior can be induced through semantics, acoustic style, signal artifacts, or internal representations. Existing work studies these risks under heterogeneous threat models and evaluation protocols, making it difficult to compare attack practicality or defense utility. This paper provides a unified taxonomy and a controlled empirical evaluation of LALM jailbreak attacks and defenses. We organize prior work into semantic, acoustic, signal, and ","authors_text":"Bo-Han Feng, Chien-Feng Liu, You-Hsuan Chang, Yu-Hsuan Li Liang, Yun-Nung Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-28T14:53:27Z","title":"Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30031","kind":"arxiv","version":1},"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:f95c292b735bc80def8281cb5269e8a3676d0dfae0f35235630805a81665d70b","target":"record","created_at":"2026-05-29T02:06:07Z","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":"e0aad4ab7e3496512b5b4e7c2bd915706caed7d65d0ece37a9134fdc5c8e1c0f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-28T14:53:27Z","title_canon_sha256":"03119461083e3a5030c7a2bb03895acb4c628f3bb0507114b1a0ed3193757b26"},"schema_version":"1.0","source":{"id":"2605.30031","kind":"arxiv","version":1}},"canonical_sha256":"01d3a1e4bb7239fe83bf5145ecaad70b4627faeb38f02a6e86846024fa509c9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01d3a1e4bb7239fe83bf5145ecaad70b4627faeb38f02a6e86846024fa509c9b","first_computed_at":"2026-05-29T02:06:07.773289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:07.773289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5HkBHSGtSq7c1LG+imQn5B+ErfUyxZhjV9misu5CSprRSlSLlsedJsFdKrSBIrZkj3RsMEdEP+Eypp3LmM4uCQ==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:07.773830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f95c292b735bc80def8281cb5269e8a3676d0dfae0f35235630805a81665d70b","sha256:64875ff843f251236c99cb9aae2f6216200b97e9f816d14c75f2d16edb8d8277"],"state_sha256":"8cf58bc7568d61aa8c198a23bb154a919aec11c5438ef6cfc92a9886ae672566"}