1 code implementation • 14 Mar 2024 • Blaine Hoak, Patrick McDaniel
In this work, we investigate \textit{texture learning}: the identification of textures learned by object classification models, and the extent to which they rely on these textures.
no code implementations • 9 Sep 2022 • Ryan Sheatsley, Blaine Hoak, Eric Pauley, Patrick McDaniel
From our evaluation we find that attack performance to be highly contextual: the domain, model robustness, and threat model can have a profound influence on attack efficacy.
no code implementations • 18 May 2021 • Ryan Sheatsley, Blaine Hoak, Eric Pauley, Yohan Beugin, Michael J. Weisman, Patrick McDaniel
Machine learning is vulnerable to adversarial examples-inputs designed to cause models to perform poorly.