Enhancing generalization in high energy physics using white-box adversarial attacks
Not on the map. Why?
Abstract (arXiv)
Machine learning is becoming increasingly popular in the context of particle physics. Supervised learning, which uses labeled Monte Carlo (MC) simulations, remains one of the most widely used methods for discriminating signals beyond the Standard Model. However, this paper suggests that supervised models may depend excessively on artifacts and approximations from Monte Carlo simulations, potentially limiting their ability to generalize well to real data. This study aims to enhance the generalization properties of supervised models by reducing the sharpness of local minima. It reviews the application of four distinct white-box adversarial attacks in the context of classifying Higgs boson decay signals. The attacks are divided into weight-space attacks and feature-space attacks. To study and quantify the sharpness of different local minima, this paper presents two analysis methods: gradient ascent and reduced Hessian eigenvalue analysis. The results show that white-box adversarial attacks significantly improve generalization performance, albeit with increased computational complexity.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 14 Nov 2024.
Builds on
31 of 53 references.
References · 31
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2019Invariant Risk Minimizationcited by 1,832
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
- 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
- 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
- 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
- 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
- 2019Fantastic Generalization Measures and Where to Find Themcited by 507
- 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
19 more
- 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
- 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 357
- 2020Understanding and Improving Fast Adversarial Trainingcited by 213
- 2018Robustness via curvature regularization, and vice versacited by 174
- 2022Towards Understanding Sharpness-Aware Minimizationcited by 145
- 2020Lorentz Group Equivariant Neural Network for Particle Physicscited by 120
- 2022Particle Transformer for Jet Taggingcited by 95
- 2018Energy Flow Networks: Deep Sets for Particle Jetscited by 83
- 2021A Living Review of Machine Learning for Particle Physicscited by 77
- 2022Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approachcited by 70
- 2022How Does Sharpness-Aware Minimization Minimize Sharpness?cited by 64
- 2022Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspectivecited by 48
- 2023PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physicscited by 27
- 2023Explainable Equivariant Neural Networks for Particle Physics: PELICANcited by 22
- 2024The Landscape of Unfolding with Machine Learningcited by 20
- 2023Sharpness-Aware Minimization Alone can Improve Adversarial Robustnesscited by 14
- 2021A Cautionary Tale of Decorrelating Theory Uncertaintiescited by 11
- 2023nu2-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flowscited by 10
- 2022Improving Robustness of Jet Tagging Algorithms with Adversarial Trainingcited by 6
Built on by
Not cited yet.