activity
20182020
most citedBatch Normalization is a Cause of Adversarial Vulnerability

54 citations · 63 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CV2020

NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results

Abdelrahman Abdelhamed, Mahmoud Afifi, Radu Timofte +87

This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results. The challenge is a new versi…

cs.CV20199 cited

Multiple-Identity Image Attacks Against Face-based Identity Verification

Jerone T. A. Andrews, Thomas Tanay, Lewis D. Griffin

Facial verification systems are vulnerable to poisoning attacks that make use of multiple-identity images (MIIs)---face images stored in a database that resemble multiple persons,…

cs.LG201954 cited

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…

cs.CV2018

A New Angle on L2 Regularization

Thomas Tanay, Lewis D Griffin

Imagine two high-dimensional clusters and a hyperplane separating them. Consider in particular the angle between: the direction joining the two clusters' centroids and the normal t…

cs.CV2018

Built-in Vulnerabilities to Imperceptible Adversarial Perturbations

Thomas Tanay, Jerone T. A. Andrews, Lewis D. Griffin

Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult. In this work we show that the reverse problem---making models m…

cs.LG2018

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…