Sign in

Effects of Loss Functions And Target Representations on Adversarial Robustness

By Sean Saito and Sujoy Roy
Understanding and evaluating the robustness of neural networks under adversarial settings is a subject of growing interest. Attacks proposed in the literature usually work with models trained to minimize cross-entropy loss and output softmax probabilities. In this work, we present interesting experimental results that suggest the importance of considering other... Show more
February 8, 2019
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Effects of Loss Functions And Target Representations on Adversarial Robustness
Click on play to start listening