# Improving Robustness of Jet Tagging Algorithms with Adversarial Training

arXiv: https://arxiv.org/abs/2203.13890 · HTML: https://mlsanity.com/paper/2203.13890/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 78 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Deep Ensembles: A Loss Landscape Perspective](https://mlsanity.com/paper/1912.02757/) (2019)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Disentangling Adversarial Robustness and Generalization](https://mlsanity.com/paper/1812.00740/) (2018)
- [Robustness of classifiers: from adversarial to random noise](https://mlsanity.com/paper/1608.08967/) (2016)
- [Learning to Pivot with Adversarial Networks](https://mlsanity.com/paper/1611.01046/) (2016)
- [Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization](https://mlsanity.com/paper/1511.05432/) (2015)
- [DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classification](https://mlsanity.com/paper/2112.14299/) (2021)
- [AI Safety for High Energy Physics](https://mlsanity.com/paper/1910.08606/) (2019)

## Built on by (most cited first, 6 of 6)

- [Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surface](https://mlsanity.com/paper/2303.14511/) (2023)
- [MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks](https://mlsanity.com/paper/2511.01352/) (2025)
- [Image and Point-cloud Classification for Jet Analysis in High-Energy Physics: A survey](https://mlsanity.com/paper/2403.11934/) (2024)
- [Exploring the Universality of Hadronic Jet Classification](https://mlsanity.com/paper/2204.03812/) (2022)
- [Enhancing generalization in high energy physics using white-box adversarial attacks](https://mlsanity.com/paper/2411.09296/) (2024)
- [Safe Domain Adaptation for Physics: Overcoming Nuisances, Label Shifts, and Simulation Priors](https://mlsanity.com/paper/2608.18190/) (2026)

## Abstract (arXiv)

Deep learning is a standard tool in the field of high-energy physics, facilitating considerable sensitivity enhancements for numerous analysis strategies. In particular, in identification of physics objects, such as jet flavor tagging, complex neural network architectures play a major role. However, these methods are reliant on accurate simulations. Mismodeling can lead to non-negligible differences in performance in data that need to be measured and calibrated against. We investigate the classifier response to input data with injected mismodelings and probe the vulnerability of flavor tagging algorithms via application of adversarial attacks. Subsequently, we present an adversarial training strategy that mitigates the impact of such simulated attacks and improves the classifier robustness. We examine the relationship between performance and vulnerability and show that this method constitutes a promising approach to reduce the vulnerability to poor modeling.