no code implementations • 1 Jun 2023 • Natalie Abreu, Nathan Vaska, Victoria Helus
We evaluate whether the method increases semantic alignment by evaluating model performance on adversarially perturbed data, with the idea that it should be easier for an adversary to switch one class to a similarly represented class.
no code implementations • 21 Nov 2022 • Natalie Abreu, Nathan Vaska, Victoria Helus
Most robust training techniques aim to improve model accuracy on perturbed inputs; as an alternate form of robustness, we aim to reduce the severity of mistakes made by neural networks in challenging conditions.