Yulun Jiang

Official source

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

About
Privacy
Disclaimer

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Sabine Süsstrunk, Mathieu Salzmann, Chen Liu, Yulun Jiang

We address the problem of stably and efficiently training a deep neural network robust to adversarial perturbations bounded by an

l_1

norm. We demonstrate that achieving robustness against

l_1

-bou

2023