LGCROct 18, 2025

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

arXiv:2510.16440v1h-index: 1
Originality Synthesis-oriented
AI Analysis

This work addresses adversarial robustness in high-energy physics, but it is incremental as it applies known gradient-based techniques to a specific competition task.

The authors tackled the problem of designing an adversarial attack to maximize misclassification with minimal perturbations for a classification model in a high-energy physics competition, achieving first place with the best results in perturbation size and fooling success rate.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes