English

A Minimax Approach Against Multi-Armed Adversarial Attacks Detection

Computer Vision and Pattern Recognition 2023-02-07 v1

Abstract

Multi-armed adversarial attacks, in which multiple algorithms and objective loss functions are simultaneously used at evaluation time, have been shown to be highly successful in fooling state-of-the-art adversarial examples detectors while requiring no specific side information about the detection mechanism. By formalizing the problem at hand, we can propose a solution that aggregates the soft-probability outputs of multiple pre-trained detectors according to a minimax approach. The proposed framework is mathematically sound, easy to implement, and modular, allowing for integrating existing or future detectors. Through extensive evaluation on popular datasets (e.g., CIFAR10 and SVHN), we show that our aggregation consistently outperforms individual state-of-the-art detectors against multi-armed adversarial attacks, making it an effective solution to improve the resilience of available methods.

Keywords

Cite

@article{arxiv.2302.02216,
  title  = {A Minimax Approach Against Multi-Armed Adversarial Attacks Detection},
  author = {Federica Granese and Marco Romanelli and Siddharth Garg and Pablo Piantanida},
  journal= {arXiv preprint arXiv:2302.02216},
  year   = {2023}
}

Comments

10 pages, 13 figures, 14 tables

R2 v1 2026-06-28T08:32:04.924Z