GATAS: Black-Box Testing of ASR Systems via Phoneme-Level Latent Space Optimization

Jul 14, 2026

Researchers have introduced GATAS, a black-box testing method that generates adversarial inputs for automatic speech recognition (ASR) systems by interpolating in the phoneme-level latent space of a text-to-speech model. GATAS achieves a 98% success rate in inducing transcription errors while maintaining high perceptual quality, outperforming both white-box and black-box baselines. The study finds that representation and perceptual alignment are more important than gradient access for generating effective adversarial test cases.

Why it matters: This work reveals a significant new vulnerability in ASR systems, showing that adversarial attacks can be highly effective even without access to model internals, which has important implications for the security of voice-driven applications.

Full story at: arXiv Cryptography and Security ↗