Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.16440 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917024574210048 |
|---|---|
| author | Stefanopoulos, Dimitris Voskou, Andreas |
| author_facet | Stefanopoulos, Dimitris Voskou, Andreas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16440 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution Stefanopoulos, Dimitris Voskou, Andreas Machine Learning Cryptography and Security 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. |
| title | Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2510.16440 |