# Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution

arXiv: https://arxiv.org/abs/2510.16440 · HTML: https://mlsanity.com/paper/2510.16440/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 3 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## Builds on (most cited first, 2 of 2)

- [Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations](https://mlsanity.com/paper/2501.05588/) (2025)
- [Introduction to the Usage of Open Data from the Large Hadron Collider for Computer Scientists in the Context of Machine Learning](https://mlsanity.com/paper/2501.06896/) (2025)

## Abstract (arXiv)

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.