Voice AI Systems Are Vulnerable to Hidden Audio Attacks
New research reveals that AI voice systems, including large audio-language models (LALMs), are susceptible to hidden audio attacks. These attacks embed imperceptible sounds into audio clips, allowing malicious actors to manipulate AI models into executing unauthorized commands with high success rates. The technique, dubbed AudioHijack, can trick models into performing actions like sensitive web searches or sending emails, even when the user is providing different instructions. AI
IMPACT AI voice systems are vulnerable to manipulation via imperceptible audio, posing risks to user data and device control.