AIBearisharXiv – CS AI · 10h ago7/10
🧠
MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations
Researchers introduced MuPPET, a benchmark testing privacy vulnerabilities in large language model assistants operating in multi-party conversations. The study reveals that LLMs leak significantly more sensitive information in group settings than in one-to-one interactions, with both frontier and smaller open-weight models showing substantial exposure risks that existing privacy defenses cannot adequately address.