Jiefeng Chen

Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training

2017 · arXiv (Cornell University)

In this paper we study leveraging confidence information induced by adversarial training to reinforce adversarial robustness of a given adversarially trained model. A natural measure of confidence is $\|F({\bf x})\|_\infty$ (i.e. how confident $F$ is …

GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems

2020 · arXiv (Cornell University)

This paper investigates an adversary's ease of attack in generating adversarial examples for real-world scenarios. We address three key requirements for practical attacks for the real-world: 1) automatically constraining the size and shape of the …