作者位次 #4/11ACL 2026Findings· Findings of ACL
H ear S ay Benchmark: Do Audio LLM s Leak What They Hear?
Jin Wang · Kaiwen Luo · Liang Lin · Weiliu Wang · Yitian Chen · Moayad Aloqaily · Xuehai Tang · Zhenhong Zhou · Kun Wang · Li Sun · Qingsong Wen
摘要
While Audio Large Language Models (ALLMs) have achieved remarkable progress in understanding and generation, their potential privacy implications remain largely unexplored. This paper takes the first step to investigate whether ALLMs inadvertently leak user privacy solely through acoustic voicepr...