This report presents the winning solution for Task 1 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery at ECML-PKDD 2025. The task required designing an adversarial attack against a provided classification model that maximizes misclassification while minimizing perturbations. Our approach employs a multi-round gradient-based strategy that leverages the differentiable structure of the model, augmented with random initialization and sample-mixing techniques to enhance effectiveness. The resulting attack achieved the best results in perturbation size and fooling success rate, securing first place in the competition.
@article{arxiv.2510.16440,
title = {Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution},
author = {Dimitris Stefanopoulos and Andreas Voskou},
journal= {arXiv preprint arXiv:2510.16440},
year = {2025}
}