collaborators

5 papers

cs.LG2025

Graph-based Integrated Gradients for Explaining Graph Neural Networks

Lachlan Simpson, Kyle Millar, Adriel Cheng +2

Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discret…

cs.LG2025

Algebraic Adversarial Attacks on Explainability Models

Lachlan Simpson, Federico Costanza, Kyle Millar +3

Classical adversarial attacks are phrased as a constrained optimisation problem. Despite the efficacy of a constrained optimisation approach to adversarial attacks, one cannot trac…

cs.LG2025

Tangentially Aligned Integrated Gradients for User-Friendly Explanations

Lachlan Simpson, Federico Costanza, Kyle Millar +3

Integrated gradients is prevalent within machine learning to address the black-box problem of neural networks. The explanations given by integrated gradients depend on a choice of…

cs.LG2025

Riemannian Integrated Gradients: A Geometric View of Explainable AI

Federico Costanza, Lachlan Simpson

We introduce Riemannian Integrated Gradients (RIG); an extension of Integrated Gradients (IG) to Riemannian manifolds. We demonstrate that RIG restricts to IG when the Riemannian m…

cs.LG2025

Algebraic Adversarial Attacks on Integrated Gradients

Lachlan Simpson, Federico Costanza, Kyle Millar +3

Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path me…