NKNet: A Deep Neural Network Framework with Defensing Against Adversarial Attacks
Jie Zou, Xiaoqing Ma, Mengqing Chen, Ya Ma, Xiaosong Zhao, Gang Bai · 2019
Adversarial attacks are a major security risk for deep neural networks (DNN) and other machine learning models, which can substantially reduce the performance of the model and make security issues on the application of the model. Hence, in order to use DNNs as a reliable method, this paper proposes a DNN framework with the capability to defensive adversarial attacks. In the framework every single DNN model is designed to be differentiate. And decisions made by the framework rely on a part of DNNs in the framework which are chosen random. This makes the framework heterogeneous, dynamic, randomly and general. In the paper, we design a verification instance. In the instance, every DNN has different data transform and the structure is unique to each other. The results of the experiment demonstrate that the framework can giving predictions accurately and reliably in different kinds of adversarial and clean samples. This indicates that the framework is an acceptable method to defense adversarial attacks.