10 citations · 24 across the 21 of their papers we have counts for
21 papers
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
Yuxi Li, Zhibo Zhang, Kailong Wang +3
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or t…
Work Zones challenge VLM Trajectory Planning: Toward Mitigation and Robust Autonomous Driving
Yifan Liao, Zhen Sun, Xiaoyun Qiu +7
Visual Language Models (VLMs), with powerful multimodal reasoning capabilities, are gradually integrated into autonomous driving by several automobile manufacturers to enhance plan…
When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
Haoran Ou, Kangjie Chen, Xingshuo Han +4
Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Inte…
Pixel-Optimization-Free Patch Attack on Stereo Depth Estimation
Hangcheng Liu, Xu Kuang, Xingshuo Han +6
Stereo Depth Estimation (SDE) is essential for scene perception in vision-based systems such as autonomous driving. Prior work shows SDE is vulnerable to pixel-optimization attacks…
SwitchPatch: Physical Adversarial Attack Strategy with Switchable Adversarial Objectives
Hanrui Jiang, Yutong Wu, Shiyi Yao +5
Physical adversarial patch (PAP) attacks attach carefully crafted patches to physical objects to manipulate a deployed model. However, existing PAP attacks suffer from several limi…
Beyond Retrieval: Improving Evidence Quality for LLM-based Multimodal Fact-Checking
Haoran Ou, Gelei Deng, Xingshuo Han +4
The increasing multimodal disinformation, where deceptive claims are reinforced through coordinated text and visual content, poses significant challenges to automated fact-checking…
Testing the Fault-Tolerance of Multi-Sensor Fusion Perception in Autonomous Driving Systems
Haoxiang Tian, Wenqiang Ding, Xingshuo Han +5
High-level Autonomous Driving Systems (ADSs), such as Google Waymo and Baidu Apollo, typically rely on multi-sensor fusion (MSF) based approaches to perceive their surroundings. Th…
SSD: A State-based Stealthy Backdoor Attack For Navigation System in UAV Route Planning
Zhaoxuan Wang, Yang Li, Jie Zhang +6
Unmanned aerial vehicles (UAVs) are increasingly employed to perform high-risk tasks that require minimal human intervention. However, UAVs face escalating cybersecurity threats, p…
An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems
Haoxiang Tian, Xingshuo Han, Guoquan Wu +5
Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep…
PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning
Zhen Sun, Tianshuo Cong, Yule Liu +5
Fine-tuning is an essential process to improve the performance of Large Language Models (LLMs) in specific domains, with Parameter-Efficient Fine-Tuning (PEFT) gaining popularity d…
Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack
Xingshuo Han, Xuanye Zhang, Xiang Lan +7
By using a control variate to calibrate the local gradient of each client, Scaffold has been widely known as a powerful solution to mitigate the impact of data heterogeneity in Fed…
The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition
Shuai Yuan, Xingshuo Han, Hongwei Li +5
Recently, traffic sign recognition (TSR) systems have become a prominent target for physical adversarial attacks. These attacks typically rely on conspicuous stickers and projectio…
LMM-enhanced Safety-Critical Scenario Generation for Autonomous Driving System Testing From Non-Accident Traffic Videos
Haoxiang Tian, Xingshuo Han, Yuan Zhou +6
Safety testing serves as the fundamental pillar for the development of autonomous driving systems (ADSs). To ensure the safety of ADSs, it is paramount to generate a diverse range…
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…
Federated Learning based on Defending Against Data Poisoning Attacks in IoT
Jiayin Li, Wenzhong Guo, Xingshuo Han +2
The rapidly expanding number of Internet of Things (IoT) devices is generating huge quantities of data, but the data privacy and security exposure in IoT devices, especially in the…
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…
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…
SoK: Rethinking Sensor Spoofing Attacks against Robotic Vehicles from a Systematic View
Yuan Xu, Xingshuo Han, Gelei Deng +3
Robotic Vehicles (RVs) have gained great popularity over the past few years. Meanwhile, they are also demonstrated to be vulnerable to sensor spoofing attacks. Although a wealth of…
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…
SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization
Wenbo Gou, Wen Shi, Jian Lou +3
Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and…