Training for faster adversarial robustness verification via inducing Relu stability

We explore the concept of co-design in the context of neural network verification. Specifically, we aim to train deep neural networks that not only are robust to adversarial perturbations but also whose robustness can be verified more easily. To this end, we identify two properties of network models...

Full description

Bibliographic Details
Main Authors: Xiao, Kai Yuanqing, Tjeng, Vincent, Shafiullah, Nur Muhammad Mahi., Mądry, Aleksander
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Format: Article
Language:English
Published: ICLR 2021
Online Access:https://hdl.handle.net/1721.1/130110