12 citations · 13 across the 10 of their papers we have counts for
10 papers
Watermarking LLM Agent Trajectories
Wenlong Meng, Chen Gong, Terry Yue Zhuo +6
LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model gene…
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…
Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion
Yi Shi, Wenlong Meng, Zhenyuan Guo +2
With the rapid rise of social media and Internet culture, memes have become a popular medium for expressing emotional tendencies. This has sparked growing interest in Meme Emotion…
GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors
Wenlong Meng, Shuguo Fan, Chengkun Wei +5
In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text (AIGT) detectors. GradEscape overcomes the undifferentiable computation…
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…
Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation
Wenlong Meng, Fan Zhang, Wendao Yao +4
Large language models (LLMs) have demonstrated significant utility in a wide range of applications; however, their deployment is plagued by security vulnerabilities, notably jailbr…
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…
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…
LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors
Chengkun Wei, Wenlong Meng, Zhikun Zhang +6
Prompt-tuning has emerged as an attractive paradigm for deploying large-scale language models due to its strong downstream task performance and efficient multitask serving ability.…
DPMLBench: Holistic Evaluation of Differentially Private Machine Learning
Chengkun Wei, Minghu Zhao, Zhikun Zhang +5
Differential privacy (DP), as a rigorous mathematical definition quantifying privacy leakage, has become a well-accepted standard for privacy protection. Combined with powerful mac…