140 citations · 189 across the 12 of their papers we have counts for
13 papers
AdaptPrint: Response-Adaptive Fingerprinting of Black-Box LLM Services
Yilin Li, Yifei Zhang, Guozhu Meng
Black-box LLM services have emerged as a practical deployment paradigm. Nevertheless, their opacity also hinders the systematic assessment of security risks and complicates copyrig…
The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again
Tong Liu, Guozhu Meng, Peng Zhou +3
Pickle deserialization vulnerabilities have persisted throughout Python's history, remaining widely recognized yet unresolved. Due to its ability to transparently save and restore…
Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks
Yingjie Zhang, Tong Liu, Zhe Zhao +2
LLMs remain vulnerable to jailbreak attacks that exploit adversarial prompts to circumvent safety measures. Current safety fine-tuning approaches face two critical limitations. Fir…
A Survey on Physical Adversarial Attacks against Face Recognition Systems
Mingsi Wang, Jiachen Zhou, Tianlin Li +2
As Face Recognition (FR) technology becomes increasingly prevalent in finance, the military, public safety, and everyday life, security concerns have grown substantially. Physical…
Dormant: Defending against Pose-driven Human Image Animation
Jiachen Zhou, Mingsi Wang, Tianlin Li +2
Pose-driven human image animation has achieved tremendous progress, enabling the generation of vivid and realistic human videos from just one single photo. However, it conversely e…
AuthNet: Neural Network with Integrated Authentication Logic
Yuling Cai, Fan Xiang, Guozhu Meng +2
Model stealing, i.e., unauthorized access and exfiltration of deep learning models, has become one of the major threats. Proprietary models may be protected by access controls and…
Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
Tong Liu, Yingjie Zhang, Zhe Zhao +3
In recent years, large language models (LLMs) have demonstrated notable success across various tasks, but the trustworthiness of LLMs is still an open problem. One specific threat…
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…
ConFL: Constraint-guided Fuzzing for Machine Learning Framework
Zhao Liu, Quanchen Zou, Tian Yu +4
As machine learning gains prominence in various sectors of society for automated decision-making, concerns have risen regarding potential vulnerabilities in machine learning (ML) f…
Understanding Real-world Threats to Deep Learning Models in Android Apps
Zizhuang Deng, Kai Chen, Guozhu Meng +3
Famous for its superior performance, deep learning (DL) has been popularly used within many applications, which also at the same time attracts various threats to the models. One pr…
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…
DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks
Yingzhe He, Guozhu Meng, Kai Chen +2
Machine unlearning has great significance in guaranteeing model security and protecting user privacy. Additionally, many legal provisions clearly stipulate that users have the righ…
A Performance-Sensitive Malware Detection System Using Deep Learning on Mobile Devices
Ruitao Feng, Sen Chen, Xiaofei Xie +3
Currently, Android malware detection is mostly performed on server side against the increasing number of malware. Powerful computing resource provides more exhaustive protection fo…