{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KUIVKFP47JRCYHD3AT6ORTDF5P","short_pith_number":"pith:KUIVKFP4","schema_version":"1.0","canonical_sha256":"55115515fcfa622c1c7b04fce8cc65ebdeaf4b8459840f771b162431eecd20de","source":{"kind":"arxiv","id":"2602.02557","version":2},"attestation_state":"computed","paper":{"title":"The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.LG","authors_text":"Adel Bibi, Aoxi Liu, Baoyuan Wu, Junchi Yu, Philip Torr, YuPeng Chen","submitted_at":"2026-01-30T14:23:50Z","abstract_excerpt":"Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment. However, whether such alignment inadvertently facilitates the transfer of safety vulnerabilities across modalities remains underexplored. This question is critical as text-based jailbreak attacks are considerably more mature than audio-based ones; if they transfer systematically, current audio safety evaluations may underestimate risks originating from the text modality. In this paper, we introduce the Alignment Curse, a formally characterized and emp"},"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":"2602.02557","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T14:23:50Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"fefce707c30a9576859ae5e43bc82e33419bf4f24f341b58b18ffa718689f84e","abstract_canon_sha256":"8cbe1da8e95b47c0b3edb5fe26b2f9236c5916580847266e1091306d040f5b60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:42.024401Z","signature_b64":"lv8UA/C0CHrzCLMy3QAYby2Hgbm2S+dN7r23lbWSFn0c2H+Tkc2Zv3U2e/EBEkWMDKza+EdXe/ysc9/2HjNDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55115515fcfa622c1c7b04fce8cc65ebdeaf4b8459840f771b162431eecd20de","last_reissued_at":"2026-06-02T01:03:42.023884Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:42.023884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.LG","authors_text":"Adel Bibi, Aoxi Liu, Baoyuan Wu, Junchi Yu, Philip Torr, YuPeng Chen","submitted_at":"2026-01-30T14:23:50Z","abstract_excerpt":"Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment. However, whether such alignment inadvertently facilitates the transfer of safety vulnerabilities across modalities remains underexplored. This question is critical as text-based jailbreak attacks are considerably more mature than audio-based ones; if they transfer systematically, current audio safety evaluations may underestimate risks originating from the text modality. In this paper, we introduce the Alignment Curse, a formally characterized and emp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02557","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/2602.02557/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":"2602.02557","created_at":"2026-06-02T01:03:42.023965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02557v2","created_at":"2026-06-02T01:03:42.023965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02557","created_at":"2026-06-02T01:03:42.023965+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUIVKFP47JRC","created_at":"2026-06-02T01:03:42.023965+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUIVKFP47JRCYHD3","created_at":"2026-06-02T01:03:42.023965+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUIVKFP4","created_at":"2026-06-02T01:03:42.023965+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/KUIVKFP47JRCYHD3AT6ORTDF5P","json":"https://pith.science/pith/KUIVKFP47JRCYHD3AT6ORTDF5P.json","graph_json":"https://pith.science/api/pith-number/KUIVKFP47JRCYHD3AT6ORTDF5P/graph.json","events_json":"https://pith.science/api/pith-number/KUIVKFP47JRCYHD3AT6ORTDF5P/events.json","paper":"https://pith.science/paper/KUIVKFP4"},"agent_actions":{"view_html":"https://pith.science/pith/KUIVKFP47JRCYHD3AT6ORTDF5P","download_json":"https://pith.science/pith/KUIVKFP47JRCYHD3AT6ORTDF5P.json","view_paper":"https://pith.science/paper/KUIVKFP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02557&json=true","fetch_graph":"https://pith.science/api/pith-number/KUIVKFP47JRCYHD3AT6ORTDF5P/graph.json","fetch_events":"https://pith.science/api/pith-number/KUIVKFP47JRCYHD3AT6ORTDF5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUIVKFP47JRCYHD3AT6ORTDF5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUIVKFP47JRCYHD3AT6ORTDF5P/action/storage_attestation","attest_author":"https://pith.science/pith/KUIVKFP47JRCYHD3AT6ORTDF5P/action/author_attestation","sign_citation":"https://pith.science/pith/KUIVKFP47JRCYHD3AT6ORTDF5P/action/citation_signature","submit_replication":"https://pith.science/pith/KUIVKFP47JRCYHD3AT6ORTDF5P/action/replication_record"}},"created_at":"2026-06-02T01:03:42.023965+00:00","updated_at":"2026-06-02T01:03:42.023965+00:00"}