Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
Published in Proceedings of IEEE S&P, 2026
This work was reported by IEEE Spectrum on May, 2026. We also have a live interview with The Agenda of Dubai Eye 103.8 to talk about this work.
Recommended citation: Meng Chen, Kun Wang, Li Lu*, Jiaheng Zhang, Tianwei Zhang. "Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection." Proceedings of IEEE S&P. San Francisco, CA, USA. 2026. doi: to appear.
