P. García Arce, R. Naveiro Flores, D. Ríos Insua

Machine learning systems are increasingly exposed to adversarial attacks. While much of the research in adversarial machine learning has focused on studying the weaknesses against evasion attacks against classification models in classical setups, the susceptibility of Bayesian regression models to attacks remains underexplored. This paper introduces a general methodology for designing optimal evasion attacks against such models. We investigate two adversarial objectives: perturbing specific point predictions and altering the entire posterior predictive distribution. For both scenarios, we propose gradient-based attacks that are applicable even when the posterior predictive distribution lacks a closed-form solution and is accessible only through Markov Chain Monte Carlo sampling.

Keywords: Adversarial Machine Learning, Bayesian Neural Networks

Scheduled

Interdisciplinary applications of Bayesian methods
June 10, 2025  3:30 PM
Sala de prensa (MR 13)


Other papers in the same session


Cookie policy

We use cookies in order to be able to identify and authenticate you on the website. They are necessary for the correct functioning of it, and therefore they can not be disabled. If you continue browsing the website, you are agreeing with their acceptance, as well as our Privacy Policy.

Additionally, we use Google Analytics in order to analyze the website traffic. They also use cookies and you can accept or refuse them with the buttons below.

You can read more details about our Cookie Policy and our Privacy Policy.