Showing 2021Show all
2 papers · 1 filter
cs.LG2021
Measuring the Contribution of Multiple Model Representations in Detecting Adversarial Instances
Daniel Steinberg, Paul Munro
Deep learning models have been used for a wide variety of tasks. They are prevalent in computer vision, natural language processing, speech recognition, and other areas. While thes…
cs.LG2021
Visualizing Representations of Adversarially Perturbed Inputs
Daniel Steinberg, Paul Munro
It has been shown that deep learning models are vulnerable to adversarial attacks. We seek to further understand the consequence of such attacks on the intermediate activations of…