Adversarial attack and interpretability of the deep neural network from the geometric perspective(几何视角下深度神经网络的对抗攻击与可解释性研究进展)

Abstract: Deep learning has achieved significant success in various engineering fields. However, its drawback has also received considerable attention recently, i.e., it suffers from poor interpretability, weak robustness and difficulty for network training, which seriously affect the security and usability of deep neural networks. Therefore adversarial attacks and interpretability become the focuses of the next generation of artificial intelligence research. In this paper, we survey recent works on them from a novel geometric perspective. We reformulate the problems in traditional deep learning models from the viewpoint of manifold theory, and summarize several strategies for possible optimization of the deep networks based on interpretability. Finally, we state several challenges on the interpretability from manifold theory and outline possible future directions.

Download paper here

More information

Recommended citation: Mengfei Xia, Zipeng Ye, Wang Zhao, Ran Yi, Yong-Jin Liu*. Adversarial attack and interpretability of the deep neural network from the geometric perspective(几何视角下深度神经网络的对抗攻击与可解释性研究进展). Scientia Sinica Informationis, Vol. 51, No. 9, pp.1411-1437, in Chinese, 2021.