207 citations · 599 across the 19 of their papers we have counts for
19 papers
A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination
Shiji Zhao, Yuxuan Zhou, Chen Xiong +3
Multimodal Large Language Models (MLLMs) have achieved impressive progress in image-text comprehension and generation, yet they remain susceptible to jailbreak attacks that can tri…
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Yihao Zhang, Kai Wang, Jiangrong Wu +7
Large Language Models (LLMs) face prominent security risks from jailbreaking, a practice that manipulates models to bypass built-in security constraints and generate unethical or u…
OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
Xiaojun Jia, Jie Liao, Qi Guo +11
Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks…
On the Adversarial Transferability of Generalized "Skip Connections"
Yisen Wang, Yichuan Mo, Dongxian Wu +3
Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification pe…
Towards Robust Model Watermark via Reducing Parametric Vulnerability
Guanhao Gan, Yiming Li, Dongxian Wu +1
Deep neural networks are valuable assets considering their commercial benefits and huge demands for costly annotation and computation resources. To protect the copyright of DNNs, b…
An Efficient Virtual Data Generation Method for Reducing Communication in Federated Learning
Cheng Yang, Xue Yang, Dongxian Wu +1
Communication overhead is one of the major challenges in Federated Learning(FL). A few classical schemes assume the server can extract the auxiliary information about training data…
When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture
Yichuan Mo, Dongxian Wu, Yifei Wang +2
Vision Transformers (ViTs) have recently achieved competitive performance in broad vision tasks. Unfortunately, on popular threat models, naturally trained ViTs are shown to provid…
On the Effectiveness of Adversarial Training against Backdoor Attacks
Yinghua Gao, Dongxian Wu, Jingfeng Zhang +4
DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor at…
Adversarial Neuron Pruning Purifies Backdoored Deep Models
Dongxian Wu, Yisen Wang
As deep neural networks (DNNs) are growing larger, their requirements for computational resources become huge, which makes outsourcing training more popular. Training in a third-pa…
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
Kuofeng Gao, Jiawang Bai, Bin Chen +2
A backdoored deep hashing model is expected to behave normally on original query images and return the images with the target label when a specific trigger pattern presents. To thi…
Multi defect detection and analysis of electron microscopy images with deep learning
Mingren Shen, Guanzhao Li, Dongxia Wu +12
Electron microscopy is widely used to explore defects in crystal structures, but human detecting of defects is often time-consuming, error-prone, and unreliable, and is not scalabl…
A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations
Mingren Shen, Guanzhao Li, Dongxia Wu +4
Videos captured using Transmission Electron Microscopy (TEM) can encode details regarding the morphological and temporal evolution of a material by taking snapshots of the microstr…
Quantifying Uncertainty in Deep Spatiotemporal Forecasting
Dongxia Wu, Liyao Gao, Xinyue Xiong +4
Deep learning is gaining increasing popularity for spatiotemporal forecasting. However, prior works have mostly focused on point estimates without quantifying the uncertainty of th…
DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting
Dongxia Wu, Liyao Gao, Xinyue Xiong +4
We introduce DeepGLEAM, a hybrid model for COVID-19 forecasting. DeepGLEAM combines a mechanistic stochastic simulation model GLEAM with deep learning. It uses deep learning to lea…
Temporal Calibrated Regularization for Robust Noisy Label Learning
Dongxian Wu, Yisen Wang, Zhuobin Zheng +1
Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets. However, labeling large-scale data can be very costly and erro…
Targeted Attack for Deep Hashing based Retrieval
Jiawang Bai, Bin Chen, Yiming Li +4
The deep hashing based retrieval method is widely adopted in large-scale image and video retrieval. However, there is little investigation on its security. In this paper, we propos…
Adversarial Weight Perturbation Helps Robust Generalization
Dongxian Wu, Shu-tao Xia, Yisen Wang
The study on improving the robustness of deep neural networks against adversarial examples grows rapidly in recent years. Among them, adversarial training is the most promising one…
Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels
Xianbin Lv, Dongxian Wu, Shu-Tao Xia
Training deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Probabilistic modeling, which consists of a classifier and a transition m…
Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
Dongxian Wu, Yisen Wang, Shu-Tao Xia +2
Skip connections are an essential component of current state-of-the-art deep neural networks (DNNs) such as ResNet, WideResNet, DenseNet, and ResNeXt. Despite their huge success in…