2 papers
cs.LG2023
Scalable Attribution of Adversarial Attacks via Multi-Task Learning
Zhongyi Guo, Keji Han, Yao Ge +2
Deep neural networks (DNNs) can be easily fooled by adversarial attacks during inference phase when attackers add imperceptible perturbations to original examples, i.e., adversaria…
cs.LG2020
Learning Task-aware Robust Deep Learning Systems
Keji Han, Yun Li, Xianzhong Long +1
Many works demonstrate that deep learning system is vulnerable to adversarial attack. A deep learning system consists of two parts: the deep learning task and the deep model. Nowad…