7 citations · 21 across the 15 of their papers we have counts for
15 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…
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…
RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
Peizhuo Lv, Mengjie Sun, Hao Wang +5
In recent years, tremendous success has been witnessed in Retrieval-Augmented Generation (RAG), widely used to enhance Large Language Models (LLMs) in domain-specific, knowledge-in…
PersonaMark: Personalized LLM watermarking for model protection and user attribution
Yuehan Zhang, Peizhuo Lv, Yinpeng Liu +5
The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confid…
MEA-Defender: A Robust Watermark against Model Extraction Attack
Peizhuo Lv, Hualong Ma, Kai Chen +6
Recently, numerous highly-valuable Deep Neural Networks (DNNs) have been trained using deep learning algorithms. To protect the Intellectual Property (IP) of the original owners ov…
DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models
Jiachen Zhou, Peizhuo Lv, Yibing Lan +3
Dataset sanitization is a widely adopted proactive defense against poisoning-based backdoor attacks, aimed at filtering out and removing poisoned samples from training datasets. Ho…
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…
A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information
Pan Li, Peizhuo Lv, Shenchen Zhu +2
Unlike traditional static deep neural networks (DNNs), dynamic neural networks (NNs) adjust their structures or parameters to different inputs to guarantee accuracy and computation…
SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
Peizhuo Lv, Pan Li, Shenchen Zhu +9
Recent years have witnessed tremendous success in Self-Supervised Learning (SSL), which has been widely utilized to facilitate various downstream tasks in Computer Vision (CV) and…
Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
Chang Yue, Peizhuo Lv, Ruigang Liang +1
With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on…
DBIA: Data-free Backdoor Injection Attack against Transformer Networks
Peizhuo Lv, Hualong Ma, Jiachen Zhou +4
Recently, transformer architecture has demonstrated its significance in both Natural Language Processing (NLP) and Computer Vision (CV) tasks. Though other network models are known…
HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
Peizhuo Lv, Pan Li, Shengzhi Zhang +4
Due to the wide use of highly-valuable and large-scale deep neural networks (DNNs), it becomes crucial to protect the intellectual property of DNNs so that the ownership of dispute…