54 citations · 100 across the 7 of their papers we have counts for
8 papers
Bounding generalization error with input compression: An empirical study with infinite-width networks
Angus Galloway, Anna Golubeva, Mahmoud Salem +3
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data. The ability to better predict GE ba…
Monitoring Shortcut Learning using Mutual Information
Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai +3
The failure of deep neural networks to generalize to out-of-distribution data is a well-known problem and raises concerns about the deployment of trained networks in safety-critica…
Batch Normalization is a Cause of Adversarial Vulnerability
Angus Galloway, Anna Golubeva, Thomas Tanay +2
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter…
Adversarial Examples as an Input-Fault Tolerance Problem
Angus Galloway, Anna Golubeva, Graham W. Taylor
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e.…
Adversarial Training Versus Weight Decay
Angus Galloway, Thomas Tanay, Graham W. Taylor
Performance-critical machine learning models should be robust to input perturbations not seen during training. Adversarial training is a method for improving a model's robustness t…
Predicting Adversarial Examples with High Confidence
Angus Galloway, Graham W. Taylor, Medhat Moussa
It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly…