135 citations · 210 across the 11 of their papers we have counts for
14 papers
How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation
Augustine N. Mavor-Parker, Kimberly A. Young, Caswell Barry +1
Exploration in environments with sparse rewards is difficult for artificial agents. Curiosity driven learning -- using feed-forward prediction errors as intrinsic rewards -- has ac…
Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples
Maximilian Mozes, Pontus Stenetorp, Bennett Kleinberg +1
Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood. In this work, we show th…
Conditional Adversarial Camera Model Anonymization
Jerone T. A. Andrews, Yidan Zhang, Lewis D. Griffin
The model of camera that was used to capture a particular photographic image (model attribution) is typically inferred from high-frequency model-specific artifacts present within t…
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,…
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…
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…
Machine learning based localization and classification with atomic magnetometers
Cameron Deans, Lewis D. Griffin, Luca Marmugi +1
We demonstrate identification of position, material, orientation and shape of objects imaged by an Rb atomic magnetometer performing electromagnetic induction imaging suppor…
Automated detection of smuggled high-risk security threats using Deep Learning
Nicolas Jaccard, Thomas W. Rogers, Edward J. Morton +1
The security infrastructure is ill-equipped to detect and deter the smuggling of non-explosive devices that enable terror attacks such as those recently perpetrated in western Euro…
A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
Thomas Tanay, Lewis Griffin
Deep neural networks have been shown to suffer from a surprising weakness: their classification outputs can be changed by small, non-random perturbations of their inputs. This adve…
Measuring and correcting wobble in large-scale transmission radiography
Thomas W. Rogers, James Ollier, Edward J. Morton +1
Large-scale transmission radiography scanners are used to image vehicles and cargo containers. Acquired images are inspected for threats by a human operator or a computer algorithm…
Automated X-ray Image Analysis for Cargo Security: Critical Review and Future Promise
Thomas W. Rogers, Nicolas Jaccard, Edward J. Morton +1
We review the relatively immature field of automated image analysis for X-ray cargo imagery. There is increasing demand for automated analysis methods that can assist in the inspec…
Better Image Segmentation by Exploiting Dense Semantic Predictions
Qiyang Zhao, Lewis D Griffin
It is well accepted that image segmentation can benefit from utilizing multilevel cues. The paper focuses on utilizing the FCNN-based dense semantic predictions in the bottom-up im…
Detection of concealed cars in complex cargo X-ray imagery using Deep Learning
Nicolas Jaccard, Thomas W. Rogers, Edward J. Morton +1
Non-intrusive inspection systems based on X-ray radiography techniques are routinely used at transport hubs to ensure the conformity of cargo content with the supplied shipping man…
Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions
Qiyang Zhao, Lewis D Griffin
Many deep Convolutional Neural Networks (CNN) make incorrect predictions on adversarial samples obtained by imperceptible perturbations of clean samples. We hypothesize that this i…