Robustness in ML
The robustness of a model is a measure of its stability with respect to perturbations of the input. We investigate and review recent developments in the field affecting the training, evaluation and deployment of ML systems.

Research feed

Blog

Can perceptual similarity metrics be used to compare adversarial attacks?

Adversarial attacks in computer vision are often bound in $\ell _{p}$ distance. This precludes comparing these techniques with …

Grigor Bezirganyan
Robustness in ML
Pill

Robust Solutions for Multi-Defender Stackelberg Security Games

Classical formulations of Multi-defender Stackelberg security games have the unpleasant property that the solutions are highly sensitive to …

Faried Abu Zaid
Robustness in ML
Pill

Variational- and Metric-based Deep Latent Space for Out-of-Distribution Detection

A new method for detection of out-of-distribution samples in classification with neural networks which does not require OOD training data.

Miguel de Benito Delgado
Robustness in ML
Pill

A Fine-Grained Analysis on Distribution Shift

The topic of how different models behave under distribution shift is studied experimentally, after a framework for quantifying distribution …

Michael Panchenko
Robustness in ML
Pill

Neural Collapse in deep classifiers during Terminal Phase of Training

Neural collapse refers to the observation that the last two layers of neural networks that were trained for a long time take a very simple, …

Michael Panchenko
Robustness in ML
Pill

Boosting Certified Robustness of L Infinity Distance Nets

Recent architectural improvements for neural network classifiers make them certifiably robust against certain types of adversarial attacks - …

Miguel De Benito Delgado
Robustness in ML
Blog

Certified error rates for neural networks

Adversarial training has been shown to improve robustness of neural networks to certain classes of data perturbations. Despite constant …

Miguel de Benito Delgado
Robustness in ML

Other series in Safety and reliability in ML systems

Anomaly detection

Many industrial applications of automated decision-making involve the detection of anomalous behaviour. Precisely defining what this means …

Safety and Reliability in ML Systems

Formal verification under uncertainty

Being able to ensure that AI systems behave as intended is essential for their adoption in many areas. This series covers formal methods for …

Safety and Reliability in ML Systems
Check all of our work