Wei, Chengkun

1. DPMLBench: Holistic Evaluation of Differentially Private Machine Learning
   2023/05/10 by Chengkun Wei, Wei, Chengkun, Minghu Zhao +13 · 3 citations
   Computer Science · #Privacy-Preserving Technologies in Data #Adversarial Robustness in Machine Learning
2. Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy
   2025/02/17 by Zhenyuan Guo, Yi Shi, Guo, Zhenyuan +9 · 3 citations
   Computer Science · Social Sciences · #Privacy-Preserving Technologies in Data #Privacy, Security, and Data Protection #Cryptography and Data Security
3. Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation
   2025/03/11 by Wenlong Meng, Fan Zhang, Meng, Wenlong +10 · 3 citations
   Computer Science · Social Sciences · #Topic Modeling #Access Control and Trust #Natural Language Processing Techniques
4. R.R.: Unveiling LLM Training Privacy through Recollection and Ranking
   2025/02/18 by Meng, Wenlong, Guo, Zhenyuan, Wu, Lenan +5 · 2 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences
5. DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
   2025/03/29 by Wei, Chengkun, Li, Weixian, Gong, Chen +1 · 2 citations
   #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)