作者位次 #2/7ACL 2026Findings· Findings of ACL
DP ^3 : Differentially Private Prompt Perturbation for Multi-turn LLM Inference
Lele Zheng · Chao Zhang · Feiyang Yuan · Ke Cheng · Tao Zhang · Anxiao Song · Yulong Shen
摘要
Large language models (LLMs) are widely used for text understanding and generation, with increasing deployment in applications involving sensitive user inputs. This raises significant privacy concerns, motivating the adoption of differential privacy (DP) to protect prompts during LLM inference. H...