papers AI Learner
The Github is limit! Click to go to the new site.

Adversarial Defense Through Network Profiling Based Path Extraction

2019-04-17
Yuxian Qiu, Jingwen Leng, Cong Guo, Quan Chen, Chao Li, Minyi Guo, Yuhao Zhu

Abstract

Recently, researchers have started decomposing deep neural network models according to their semantics or functions. Recent work has shown the effectiveness of decomposed functional blocks for defending adversarial attacks, which add small input perturbation to the input image to fool the DNN models. This work proposes a profiling-based method to decompose the DNN models to different functional blocks, which lead to the effective path as a new approach to exploring DNNs’ internal organization. Specifically, the per-image effective path can be aggregated to the class-level effective path, through which we observe that adversarial images activate effective path different from normal images. We propose an effective path similarity-based method to detect adversarial images with an interpretable model, which achieve better accuracy and broader applicability than the state-of-the-art technique.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.08089

PDF

http://arxiv.org/pdf/1904.08089


Similar Posts

Comments