23 citations · 32 across the 6 of their papers we have counts for
7 papers
Towards Generating Adversarial Examples on Mixed-type Data
Han Xu, Menghai Pan, Zhimeng Jiang +4
The existence of adversarial attacks (or adversarial examples) brings huge concern about the machine learning (ML) model's safety issues. For many safety-critical ML tasks, such as…
Jointly Attacking Graph Neural Network and its Explanations
Wenqi Fan, Wei Jin, Xiaorui Liu +7
Graph Neural Networks (GNNs) have boosted the performance for many graph-related tasks. Despite the great success, recent studies have shown that GNNs are highly vulnerable to adve…
Imbalanced Adversarial Training with Reweighting
Wentao Wang, Han Xu, Xiaorui Liu +3
Adversarial training has been empirically proven to be one of the most effective and reliable defense methods against adversarial attacks. However, almost all existing studies abou…
Towards the Memorization Effect of Neural Networks in Adversarial Training
Han Xu, Xiaorui Liu, Wentao Wang +5
Recent studies suggest that ``memorization'' is one important factor for overparameterized deep neural networks (DNNs) to achieve optimal performance. Specifically, the perfectly f…
To be Robust or to be Fair: Towards Fairness in Adversarial Training
Han Xu, Xiaorui Liu, Yaxin Li +2
Adversarial training algorithms have been proved to be reliable to improve machine learning models' robustness against adversarial examples. However, we find that adversarial train…
Yet Meta Learning Can Adapt Fast, It Can Also Break Easily
Han Xu, Yaxin Li, Xiaorui Liu +2
Meta learning algorithms have been widely applied in many tasks for efficient learning, such as few-shot image classification and fast reinforcement learning. During meta training,…
Adversarial Attacks and Defenses in Images, Graphs and Text: A Review
Han Xu, Yao Ma, Haochen Liu +4
Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised conc…