#asr-security News & Analysis

2 articles tagged with #asr-security. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBearisharXiv – CS AI · Jun 87/10

🧠

Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks

Researchers demonstrate a new adversarial attack called Semantic Gambit that exploits Large Language Models to significantly compromise real-time Automatic Speech Recognition systems. By leveraging predictive context from LLMs, the attack achieves a 35.6% Word Error Rate—three times higher than previously documented attacks—revealing a critical vulnerability in ASR pipelines that operate under temporal constraints.

AIBearisharXiv – CS AI · Jun 57/10

🧠

Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition

Researchers have developed a new adversarial attack method against automatic speech recognition systems that operates in feature space rather than directly on audio waveforms, achieving significantly higher transfer rates to black-box ASR models and bypassing existing defenses. The attack uses self-supervised learning representations and vocoders to reconstruct adversarial signals, revealing critical vulnerabilities in current ASR robustness evaluation protocols.