activity
20122024
most citedHealth Data in an Open World

33 citations · 96 across the 22 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2023

It's Simplex! Disaggregating Measures to Improve Certified Robustness

Andrew C. Cullen, Paul Montague, Shijie Liu +2

Certified robustness circumvents the fragility of defences against adversarial attacks, by endowing model predictions with guarantees of class invariance for attacks up to a calcul…

cs.LG2023

Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks

Shijie Liu, Andrew C. Cullen, Paul Montague +2

Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they…

cs.LG20222 cited

Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity

Andrew C. Cullen, Paul Montague, Shijie Liu +2

In response to subtle adversarial examples flipping classifications of neural network models, recent research has promoted certified robustness as a solution. There, invariance of…

cs.LG2022

Unlabelled Sample Compression Schemes for Intersection-Closed Classes and Extremal Classes

J. Hyam Rubinstein, Benjamin I. P. Rubinstein

The sample compressibility of concept classes plays an important role in learning theory, as a sufficient condition for PAC learnability, and more recently as an avenue for robust…

cs.LG20211 cited

Local Intrinsic Dimensionality Signals Adversarial Perturbations

Sandamal Weerasinghe, Tansu Alpcan, Sarah M. Erfani +2

The vulnerability of machine learning models to adversarial perturbations has motivated a significant amount of research under the broad umbrella of adversarial machine learning. S…

cs.LG2021

TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness

Zhuolin Yang, Linyi Li, Xiaojun Xu +6

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from diff…