# Colliding with Adversaries at ECML-PKDD 2025 Model Robustness Competition 1st Prize Solution

arXiv: https://arxiv.org/abs/2510.16443 · HTML: https://mlsanity.com/paper/2510.16443/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 9 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [On Embeddings for Numerical Features in Tabular Deep Learning](https://mlsanity.com/paper/2203.05556/) (2022)
- [Local Competition and Stochasticity for Adversarial Robustness in Deep Learning](https://mlsanity.com/paper/2101.01121/) (2021)
- [Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness](https://mlsanity.com/paper/2112.02671/) (2021)
- [Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations](https://mlsanity.com/paper/2501.05588/) (2025)
- [Transformers with Stochastic Competition for Tabular Data Modelling](https://mlsanity.com/paper/2407.13238/) (2024)
- [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)
- [Volvo Discovery Challenge at ECML-PKDD 2024](https://mlsanity.com/paper/2409.11446/) (2024)

## Abstract (arXiv)

This report presents the winning solution for Task 2 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery at ECML-PKDD 2025. The goal of the challenge was to design and train a robust ANN-based model capable of achieving high accuracy in a binary classification task on both clean and adversarial data generated with the Random Distribution Shuffle Attack (RDSA). Our solution consists of two components: a data generation phase and a robust model training phase. In the first phase, we produced 15 million artificial training samples using a custom methodology derived from Random Distribution Shuffle Attack (RDSA). In the second phase, we introduced a robust architecture comprising (i)a Feature Embedding Block with shared weights among features of the same type and (ii)a Dense Fusion Tail responsible for the final prediction. Training this architecture on our adversarial dataset achieved a mixed accuracy score of 80%, exceeding the second-place solution by two percentage points.