English

Tropical Bisectors and Carlini-Wagner Attacks

Machine Learning 2025-03-31 v1 Algebraic Geometry Combinatorics Metric Geometry Optimization and Control

Abstract

Pasque et al. showed that using a tropical symmetric metric as an activation function in the last layer can improve the robustness of convolutional neural networks (CNNs) against state-of-the-art attacks, including the Carlini-Wagner attack. This improvement occurs when the attacks are not specifically adapted to the non-differentiability of the tropical layer. Moreover, they showed that the decision boundary of a tropical CNN is defined by tropical bisectors. In this paper, we explore the combinatorics of tropical bisectors and analyze how the tropical embedding layer enhances robustness against Carlini-Wagner attacks. We prove an upper bound on the number of linear segments the decision boundary of a tropical CNN can have. We then propose a refined version of the Carlini-Wagner attack, specifically tailored for the tropical architecture. Computational experiments with MNIST and LeNet5 showcase our attacks improved success rate.

Cite

@article{arxiv.2503.22653,
  title  = {Tropical Bisectors and Carlini-Wagner Attacks},
  author = {Gillian Grindstaff and Julia Lindberg and Daniela Schkoda and Miruna-Stefana Sorea and Ruriko Yoshida},
  journal= {arXiv preprint arXiv:2503.22653},
  year   = {2025}
}

Comments

23 pages, 8 figures, 5 tables, 1 appendix

R2 v1 2026-06-28T22:38:22.038Z