50 citations · 157 across the 32 of their papers we have counts for
32 papers
Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks
Xiaomei Zhang, Zhaoxi Zhang, Yanjun Zhang +4
Textual adversarial examples pose serious threats to the reliability of natural language processing systems. Recent studies suggest that adversarial examples tend to deviate from t…
BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
Hangtao Zhang, Chenyu Zhu, Xianlong Wang +9
Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensi…
ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification
Xianlong Wang, Shengshan Hu, Yechao Zhang +5
Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victi…
Large Language Model Watermark Stealing With Mixed Integer Programming
Zhaoxi Zhang, Xiaomei Zhang, Yanjun Zhang +5
The Large Language Model (LLM) watermark is a newly emerging technique that shows promise in addressing concerns surrounding LLM copyright, monitoring AI-generated text, and preven…
DarkFed: A Data-Free Backdoor Attack in Federated Learning
Minghui Li, Wei Wan, Yuxuan Ning +4
Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real cli…
Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
Hangtao Zhang, Shengshan Hu, Yichen Wang +5
Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor a…
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
Ziqi Zhou, Minghui Li, Wei Liu +7
With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trai…
Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation
Di Mi, Yanjun Zhang, Leo Yu Zhang +4
Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim deep neural network (DNN) model by only querying its API service remotely, posing a se…
MISA: Unveiling the Vulnerabilities in Split Federated Learning
Wei Wan, Yuxuan Ning, Shengshan Hu +4
\textit{Federated learning} (FL) and \textit{split learning} (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping…
Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics
Xiaoxing Mo, Yechao Zhang, Leo Yu Zhang +5
A backdoor attack in deep learning inserts a hidden backdoor in the model to trigger malicious behavior upon specific input patterns. Existing detection approaches assume a metric…
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning
Ziqi Zhou, Shengshan Hu, Minghui Li +3
Multimodal contrastive learning aims to train a general-purpose feature extractor, such as CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit…
Downstream-agnostic Adversarial Examples
Ziqi Zhou, Shengshan Hu, Ruizhi Zhao +4
Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users…
Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples
Qiufan Ji, Lin Wang, Cong Shi +3
Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerable to adversarial examples, threatening their practical deployment. Despite the many research endeavors have…
A Four-Pronged Defense Against Byzantine Attacks in Federated Learning
Wei Wan, Shengshan Hu, Minghui Li +4
\textit{Federated learning} (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to v…
Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
Yechao Zhang, Shengshan Hu, Leo Yu Zhang +5
Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different…
Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning
Hangtao Zhang, Zeming Yao, Leo Yu Zhang +4
Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisonin…
Masked Language Model Based Textual Adversarial Example Detection
Xiaomei Zhang, Zhaoxi Zhang, Qi Zhong +4
Adversarial attacks are a serious threat to the reliable deployment of machine learning models in safety-critical applications. They can misguide current models to predict incorrec…
Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
Xiaogeng Liu, Minghui Li, Haoyu Wang +5
Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can pr…
Feature Extraction Matters More: Universal Deepfake Disruption through Attacking Ensemble Feature Extractors
Long Tang, Dengpan Ye, Zhenhao Lu +4
Adversarial example is a rising way of protecting facial privacy security from deepfake modification. To prevent massive facial images from being illegally modified by various deep…
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples
Shengshan Hu, Junwei Zhang, Wei Liu +5
Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While v…
Shielding Federated Learning: Mitigating Byzantine Attacks with Less Constraints
Minghui Li, Wei Wan, Jianrong Lu +5
Federated learning is a newly emerging distributed learning framework that facilitates the collaborative training of a shared global model among distributed participants with their…
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
Shengshan Hu, Ziqi Zhou, Yechao Zhang +4
Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonst…
Evaluating Membership Inference Through Adversarial Robustness
Zhaoxi Zhang, Leo Yu Zhang, Xufei Zheng +2
The usage of deep learning is being escalated in many applications. Due to its outstanding performance, it is being used in a variety of security and privacy-sensitive areas in add…
Towards Privacy-Preserving Neural Architecture Search
Fuyi Wang, Leo Yu Zhang, Lei Pan +2
Machine learning promotes the continuous development of signal processing in various fields, including network traffic monitoring, EEG classification, face identification, and many…