activity
20182023
most citedAttacking deep networks with surrogate-based adversarial black-box methods is easy

10 citations · 10 across the 2 of their papers we have counts for

collaborators

6 papers

cs.RO2023

Attacking Motion Planners Using Adversarial Perception Errors

Jonathan Sadeghi, Nicholas A. Lord, John Redford +1

Autonomous driving (AD) systems are often built and tested in a modular fashion, where the performance of different modules is measured using task-specific metrics. These metrics s…

cs.LG202210 cited

Attacking deep networks with surrogate-based adversarial black-box methods is easy

Nicholas A. Lord, Romain Mueller, Luca Bertinetto

A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existi…

cs.CV2019

Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks

Luca Bertinetto, Romain Mueller, Konstantinos Tertikas +2

Deep neural networks have improved image classification dramatically over the past decade, but have done so by focusing on performance measures that treat all classes other than th…

cs.CV2018

Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade

Tommaso Cavallari, Stuart Golodetz, Nicholas A. Lord +4

Camera pose estimation is an important problem in computer vision. Common techniques either match the current image against keyframes with known poses, directly regress the pose, o…

cs.CV2018

With Friends Like These, Who Needs Adversaries?

Saumya Jetley, Nicholas A. Lord, Philip H. S. Torr

The vulnerability of deep image classification networks to adversarial attack is now well known, but less well understood. Via a novel experimental analysis, we illustrate some fac…

cs.CV2018

Learn To Pay Attention

Saumya Jetley, Nicholas A. Lord, Namhoon Lee +1

We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module takes as input the 2D feature ve…