activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Are We Measuring Oversmoothing in Graph Neural Networks Correctly?

Kaicheng Zhang, Piero Deidda, Desmond Higham +1

Oversmoothing is a fundamental challenge in graph neural networks (GNNs): as the number of layers increases, node embeddings become increasingly similar, and model performance drop…

cs.LG2025

Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models

Lucas Beerens, Desmond J. Higham

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiri…

cs.LG2024

The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning

Alexander Bastounis, Alexander N. Gorban, Anders C. Hansen +5

In this work, we assess the theoretical limitations of determining guaranteed stability and accuracy of neural networks in classification tasks. We consider classical distribution-…

cs.LG2024

How adversarial attacks can disrupt seemingly stable accurate classifiers

Oliver J. Sutton, Qinghua Zhou, Ivan Y. Tyukin +3

Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically,…

cs.LG2024

Deceptive Diffusion: Generating Synthetic Adversarial Examples

Lucas Beerens, Catherine F. Higham, Desmond J. Higham

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb…