2 citations · 11 across the 25 of their papers we have counts for
25 papers
Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
Zihan Wang, Rui Zhang, Yu Liu +4
Large language model (LLM) agents increasingly rely on skills to package reusable capabilities through instructions, tools, and resources. High-quality skills embed expert knowledg…
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
Rui Zhang, Hongwei Li, Yun Shen +6
The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthines…
Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
Rui Zhang, Zihan Wang, Tianli Yang +5
Vision-Language Models (VLMs) are increasingly deployed in real-world applications, but their high inference cost makes them vulnerable to resource consumption attacks. Prior attac…
ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
Zihan Wang, Rui Zhang, Hongwei Li +4
Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods,…
FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
Shuai Yuan, Guowen Xu, Hongwei Li +5
Traffic sign recognition (TSR) systems are crucial for autonomous driving but are vulnerable to backdoor attacks. Existing physical backdoor attacks either lack stealth, provide in…
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
Rui Zhang, Yun Shen, Hongwei Li +5
Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however,…
MPMA: Preference Manipulation Attack Against Model Context Protocol
Zihan Wang, Rui Zhang, Yu Liu +5
Model Context Protocol (MCP) standardizes interface mapping for large language models (LLMs) to access external data and tools, which revolutionizes the paradigm of tool selection…
Combinational Backdoor Attack against Customized Text-to-Image Models
Wenbo Jiang, Jiaming He, Hongwei Li +6
Recently, Text-to-Image (T2I) synthesis technology has made tremendous strides. Numerous representative T2I models have emerged and achieved promising application outcomes, such as…
OnePath: Efficient and Privacy-Preserving Decision Tree Inference in the Cloud
Shuai Yuan, Hongwei Li, Xinyuan Qian +1
The vast storage capacity and computational power of cloud servers have led to the widespread outsourcing of machine learning inference services. While offering significant operati…
Backdoor Attacks against Image-to-Image Networks
Wenbo Jiang, Hongwei Li, Jiaming He +4
Recently, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks such as image super-resolution and denoising. Despite their remarkable…
Mercury: An Automated Remote Side-channel Attack to Nvidia Deep Learning Accelerator
Xiaobei Yan, Xiaoxuan Lou, Guowen Xu +4
DNN accelerators have been widely deployed in many scenarios to speed up the inference process and reduce the energy consumption. One big concern about the usage of the accelerator…
Alleviating the Effect of Data Imbalance on Adversarial Training
Guanlin Li, Guowen Xu, Tianwei Zhang
In this paper, we study adversarial training on datasets that obey the long-tailed distribution, which is practical but rarely explored in previous works. Compared with conventiona…
Extracting Cloud-based Model with Prior Knowledge
Shiqian Zhao, Kangjie Chen, Meng Hao +4
Machine Learning-as-a-Service, a pay-as-you-go business pattern, is widely accepted by third-party users and developers. However, the open inference APIs may be utilized by malicio…
Efficiency Boosting of Secure Cross-platform Recommender Systems over Sparse Data
Hao Ren, Guowen Xu, Tianwei Zhang +4
Fueled by its successful commercialization, the recommender system (RS) has gained widespread attention. However, as the training data fed into the RS models are often highly sensi…
A Benchmark of Long-tailed Instance Segmentation with Noisy Labels
Guanlin Li, Guowen Xu, Tianwei Zhang
In this paper, we consider the instance segmentation task on a long-tailed dataset, which contains label noise, i.e., some of the annotations are incorrect. There are two main reas…
New Secure Sparse Inner Product with Applications to Machine Learning
Guowen Xu, Shengmin Xu, Jianting Ning +4
Sparse inner product (SIP) has the attractive property of overhead being dominated by the intersection of inputs between parties, independent of the actual input size. It has intri…
VerifyML: Obliviously Checking Model Fairness Resilient to Malicious Model Holder
Guowen Xu, Xingshuo Han, Gelei Deng +5
In this paper, we present VerifyML, the first secure inference framework to check the fairness degree of a given Machine learning (ML) model. VerifyML is generic and is immune to a…
Hercules: Boosting the Performance of Privacy-preserving Federated Learning
Guowen Xu, Xingshuo Han, Shengmin Xu +4
In this paper, we address the problem of privacy-preserving federated neural network training with users. We present Hercules, an efficient and high-precision training framewor…
Privacy-preserving Decentralized Deep Learning with Multiparty Homomorphic Encryption
Guowen Xu, Guanlin Li, Shangwei Guo +2
Decentralized deep learning plays a key role in collaborative model training due to its attractive properties, including tolerating high network latency and less prone to single-po…
A Secure Fingerprinting Framework for Distributed Image Classification
Guowen Xu, Xingshuo Han, Anguo Zhang +1
The deep learning (DL) technology has been widely used for image classification in many scenarios, e.g., face recognition and suspect tracking. Such a highly commercialized applica…
SIMC 2.0: Improved Secure ML Inference Against Malicious Clients
Guowen Xu, Xingshuo Han, Tianwei Zhang +5
In this paper, we study the problem of secure ML inference against a malicious client and a semi-trusted server such that the client only learns the inference output while the serv…
ShiftNAS: Towards Automatic Generation of Advanced Mulitplication-Less Neural Networks
Xiaoxuan Lou, Guowen Xu, Kangjie Chen +3
Multiplication-less neural networks significantly reduce the time and energy cost on the hardware platform, as the compute-intensive multiplications are replaced with lightweight b…
Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving
Xingshuo Han, Guowen Xu, Yuan Zhou +3
Modern autonomous vehicles adopt state-of-the-art DNN models to interpret the sensor data and perceive the environment. However, DNN models are vulnerable to different types of adv…
Fingerprinting Image-to-Image Generative Adversarial Networks
Guanlin Li, Guowen Xu, Han Qiu +5
Generative Adversarial Networks (GANs) have been widely used in various application scenarios. Since the production of a commercial GAN requires substantial computational and human…