{"data":{"id":"af667066-0c55-48ef-9002-6266c8dd9bea","title":"Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer","summary":"This paper shows that speech tokenizers, the front ends that encode audio for ASR systems and large audio-language models, are fragile at the semantic level. The authors propose T-SemAttack, a transferable attack that uses an ensemble of semantic encoders to disrupt speech content while preserving perceptual quality, and report strong transfer to 9 open-source and black-box ASR systems and 4 LALMs. They also introduce ROSETok, a robust tokenizer built with noisy training and robust semantic distillation.","solution":"ROSETok, a robust speech tokenizer that combines noisy training with robust semantic distillation, is proposed to improve reconstruction fidelity and downstream SpeechLLM robustness.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.14929v1","publishedAt":"2026-11-11T02:33:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["speech tokenizers","SpeechLLM","large audio-language models (LALMs)","automatic speech recognition (ASR) systems"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-11T02:33:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","availability"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}