arXiv Machine Learning October 9, 2026 By Ali Alavi, Donald S. Williamson

How Hackable Is Your Speech Quality Metric? A Corrected Protocol, a Benchmark, and What Patching Buys

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

Hugging Face Trending Papers

Oct 7

How Hackable Is Your Speech Quality Metric? A Corrected Protocol, a Benchmark, and What Patching Buys

Speech quality predictors are increasingly used as rewards, yet no agreed measure of their hackability exists. The usual measurement has two flaws. First, the perturbation reaches the predictor throug...

benchmarks

arXiv AI

Jun 8

Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks

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

llms multimodal benchmarks safety

arXiv AI

Sep 12

Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems

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

multimodal benchmarks safety

arXiv Machine Learning

Oct 21

You Are the Trigger: Speaker-Activated Backdoors

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

llms agents fine-tuning multimodal

arXiv AI

Jun 29

What Was That Again? Certified Robustness for Automatic Speech Recognition

arXiv:2606. 27698v1 Announce Type: cross Abstract: Automatic Speech Recognition systems are notoriously both sensitive to adversarial and benign perturbations.

By Andrew C. Cullen, Neil Marchant, Jiani Xie, Paul Montague, Benjamin I. P. Rubinstein

multimodal safety

arXiv AI

Sep 24

Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models

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

agents robotics efficiency safety

One email a morning, machine-written

Related stories

How Hackable Is Your Speech Quality Metric? A Corrected Protocol, a Benchmark, and What Patching Buys

Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks

Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems

You Are the Trigger: Speaker-Activated Backdoors

What Was That Again? Certified Robustness for Automatic Speech Recognition

Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models