5 papers
PrivCode++: Latent-Conditioned Differentially Private Code Generation for Comprehensive Guarantees
Zheng Liu, Chen Gong, Terry Yue Zhuo +6
Large language models fine-tuned on instruction-code pairs may memorize and subsequently leak sensitive training data. Existing differentially private (DP) code generation methods…
Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
Zhenyuan Guo, Tong Chen, Wenlong Meng +4
Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer. However, these extended generations inc…
R.R.: Unveiling LLM Training Privacy through Recollection and Ranking
Wenlong Meng, Zhenyuan Guo, Lenan Wu +5
Large Language Models (LLMs) pose significant privacy risks, potentially leaking training data due to implicit memorization. Existing privacy attacks primarily focus on membership…
DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
Chengkun Wei, Weixian Li, Chen Gong +1
Differentially Private Stochastic Gradient Descent (DP-SGD) is a widely adopted technique for privacy-preserving deep learning. A critical challenge in DP-SGD is selecting the opti…
Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy
Zhenyuan Guo, Yi Shi, Wenlong Meng +3
Model merging is a widespread technology in large language models (LLMs) that integrates multiple task-specific LLMs into a unified one, enabling the merged model to inherit the sp…