Papers › Adversarial Robustness Guarantees for Classification with Gaussian Processes
Adversarial Robustness Guarantees for Classification with Gaussian Processes
Arno Blaas, Andrea Patane, Luca Laurenti, Luca Cardelli, Marta Kwiatkowska, Stephen Roberts
We investigate adversarial robustness of Gaussian Process Classification (GPC) models. Given a compact subset of the input space T⊆ℝᵈ enclosing a test point x^* and a GPC trained on a dataset 𝒟, we aim to compute the minimum and the maximum classification probability for the GPC over all the points in T. In order to do so, we show how functions lower- and upper-bounding the GPC output in T can be derived, and implement those in a branch and bound optimisation algorithm. For any error threshold ϵ> 0 selected a priori, we show that our algorithm is guaranteed to reach values ϵ-close to the actual values in finitely many iterations. We apply our method to investigate the robustness of GPC models on a 2D synthetic dataset, the SPAM dataset and a subset of the MNIST dataset, providing comparisons of different GPC training techniques, and show how our method can be used for interpretability analysis. Our empirical analysis suggests that GPC robustness increases with more accurate posterior estimation.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections