Inaudible Audio Attacks Can Hijack AI Voice Models, Study Finds – Decrypt
In brief Researchers at Zhejiang University developed AudioHijack, which hides imperceptible commands in audio to manipulate large audio-language models with a 79–96% success rate. The attack transferred from open models to commercial voice AI from Microsoft and Mistral; most standard defenses stopped only a small fraction of attempts. The team is now investigating whether the...
What's Your Reaction?
Like
0
Dislike
0
Love
0
Funny
0
Angry
0
Sad
0
Wow
0
