The Pros and Cons of Adversarial Robustness

Yacine Izza, Joao Marques-Silva

2025

Abstract

Robustness is widely regarded as a fundamental problem in the analysis of machine learning (ML) models. Most often robustness equates with deciding the non-existence of adversarial examples, where adversarial examples denote situations where small changes on some inputs cause a change in the prediction. The perceived importance of ML model robustness explains the continued progress observed for most of the last decade. Whereas robustness is often assessed locally, i.e. given some target point in feature space, robustness can also be defined globally, i.e. where any point in feature space can be considered. The importance of ML model robustness is illustrated for example by the existing competition on neural network (NN) verification (VNN-COMP), which assesses the progress of robustness tools for NNs, but also by efforts towards robustness certification. More recently, robustness tools have also been used for computing rigorous explanations of ML models. Despite the continued advances in robustness, this paper uncovers some limitations with existing definitions of robustness, both global and local, but also with efforts towards robustness certification. The paper also investigates uses of adversarial examples besides those related with robustness.

Paper Citation

in Harvard Style

Izza Y. and Marques-Silva J. (2025). The Pros and Cons of Adversarial Robustness. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 386-397. DOI: 10.5220/0013166300003890

in Bibtex Style

@conference{icaart25,
author={Yacine Izza and Joao Marques-Silva},
title={The Pros and Cons of Adversarial Robustness},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={386-397},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013166300003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - The Pros and Cons of Adversarial Robustness
SN - 978-989-758-737-5
AU - Izza Y.
AU - Marques-Silva J.
PY - 2025
SP - 386
EP - 397
DO - 10.5220/0013166300003890
PB - SciTePress