5 papers
Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning
Zeyu Jiang, Hai Huang, Xingquan Zuo
Deep reinforcement learning (DRL) has successfully addressed many complex control problems. However, the neural networks representing policies or values remain opaque, undermining…
Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective
Chang Liu, Hai Huang, Yujie Xing +1
Graph Neural Networks (GNNs) have achieved notable success in tasks such as social and transportation networks. However, recent studies have highlighted the vulnerability of GNNs t…
RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features
Jialei Song, Xingquan Zuo, Feiyang Wang +2
Deep neural networks (DNNs) are highly susceptible to adversarial samples, raising concerns about their reliability in safety-critical tasks. Currently, methods of evaluating adver…
Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective
Chang Liu, Hai Huang, Yujie Xing +1
The robustness of Graph Neural Networks (GNNs) has become an increasingly important topic due to their expanding range of applications. Various attack methods have been proposed to…
ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks
Feiyang Wang, Xingquan Zuo, Hai Huang +1
Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These a…