Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
Published in Proceedings of IEEE S&P, 2026
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.
IEEE Symposium on Security and Privacy is the premier forum for presenting developments in computer security and electronic privacy, and for bringing together researchers and practitioners in the field. IEEE S&P is a Top-four security and CCF-A conference.