8 papers
Differentially Private Natural Gradient Descent
Pan Li, Kai Chen, Shuai Chang +3
Under a fixed privacy budget, the utility of differentially private (DP) training is ultimately determined by its optimization efficiency. Standard first-order DP optimizers such a…
Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models
Yuchen Chen, Weisong Sun, Haocheng Huang +11
Code Language Models (CodeLMs) have become integral to software engineering, significantly advancing code intelligence tasks. However, their widespread adoption has raised critical…
Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines
Yifei Ge, Weisong Sun, Jinkun Xiao +8
Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, and the underlying system. For…
PuzzleMark: Implicit Jigsaw Learning for Robust Code Dataset Watermarking in Neural Code Completion Models
Haocheng Huang, Yuchen Chen, Weisong Sun +5
Constructing and curating high-quality code datasets requires significant resources, making them valuable intellectual property. Unfortunately, these datasets currently face severe…
A Model Stealing Attack Against Multi-Exit Networks
Li Pan, Lv Peizhuo, Chen Kai +3
Compared to traditional neural networks with a single output channel, a multi-exit network has multiple exits that allow for early outputs from the model's intermediate layers, thu…
LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs
Peizhuo Lv, Yiran Xiahou, Congyi Li +4
LoRA (Low-Rank Adaptation) has achieved remarkable success in the parameter-efficient fine-tuning of large models. The trained LoRA matrix can be integrated with the base model thr…