The paper introduces a corrected protocol for measuring the hackability of speech quality predictors, addressing two key flaws in previous methods. Using this protocol, it finds that four published predictors vary widely in vulnerability, with NISQA being the most hackable. The study also audits an attack‑detect‑patch loop, showing it only hardens predictors within its own attack space and can even reduce performance.
By Ali Alavi, Donald S. Williamson
arXiv:2606. 06833v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription decisions are inherently made on incomplete information.
By Jiani Xie, Andrew C. Cullen, Paul Montague, Benjamin I. P. Rubinstein
The paper introduces the Spectral Masking and Interpolation Attack (SMIA), a black‑box adversarial technique that subtly alters inaudible frequency regions of AI‑generated audio to fool voice authentication systems and their countermeasures. Experiments show SMIA achieves at least 82% success against combined verification and countermeasure systems, 97.5% against standalone speaker verification, and 100% against countermeasures, revealing a critical security gap. The authors argue that current static defenses are inadequate and call for dynamic, context‑aware defenses that can adapt to evolving threats.
By Kamel Kamel, Hridoy Sankar Dutta, Keshav Sood, Sunil Aryal
arXiv:2610.27210v1 Announce Type: new
Abstract: Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing audio backdoors require an attack...
By Nata\v{s}a Kr\v{c}o, Euodia Dodd, Peter Romov, Yves-Alexandre de Montjoye
arXiv:2609.27378v1 Announce Type: cross
Abstract: End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipu...
By Kian Shamsaie, Iman Modarressi
arXiv:2604. 09222v2 Announce Type: replace-cross Abstract: Audio Large Language Models (ALLMs) enable spoken interaction but introduce new jailbreak vulnerabilities.
By Yunqiang Wang, Hengyuan Na, Di Wu, Miao Hu, Guocong Quan
The paper investigates how acoustic and content-oriented speaker verification attacks perform against multilingual voice anonymization. It evaluates both attacker types on anonymized speech, builds a multilingual voice-converted dataset to enhance cross‑lingual generalization, and finds that attack success depends on how much linguistic utility is preserved. Acoustic‑oriented attacks generally outperform content‑oriented ones, but the performance gap narrows when linguistic information is well maintained, and the new dataset improves results while reducing cross‑lingual disparities.
By Ridwan Arefeen, Ze Li, Rong Tong, Ming Li, Xiaoxiao Miao
The paper introduces an adaptive jailbreak attack framework that evaluates both cascaded pipelines and end‑to‑end large audio‑language models (LALMs) under a unified setting. It employs a feedback‑guided mutation engine to automatically generate and refine jailbreak candidates across textual prompts and audio perturbations, thereby broadening attack diversity. Experiments on six audio‑based systems show that both paradigms remain highly vulnerable, with the framework achieving higher attack success rates than existing methods.
By Linghan Huang, Bo Li, Huaming Chen, Kim-Kwang Raymond Choo
arXiv:2605.14605v3 Announce Type: replace-cross
Abstract: Model providers increasingly release the weights of large language models. Although these models are safety-aligned before release, their saf...
By Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky
arXiv:2609.13150v1 Announce Type: cross
Abstract: Reference-free quality predictors such as UTMOS, DNSMOS and SCOREQ are the de facto automatic evaluators for text-to-speech (TTS) and are increasingl...
By Antonis Asonitis, Juan Pablo Zuluaga Gomez, Francesco Verdini, Aref Farhadipour, Marzieh Razavi, Pierre-Edouard Honnet, Vijeta Avijeet
arXiv:2602. 02557v2 Announce Type: replace-cross Abstract: Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment.
By Yupeng Chen, Junchi Yu, Aoxi Liu, Baoyuan Wu, Philip Torr, Adel Bibi
arXiv:2606. 18193v1 Announce Type: cross Abstract: We evaluate the adversarial robustness of two frontier large language models (LLMs) developed by Anthropic, Fable 5 and Opus 4.
By Nicola Franco