mlsanityData to 7 Oct 2026

Improving Robustness of Jet Tagging Algorithms with Adversarial Training

arXiv 2203.13890 ↗First posted 25 Mar 2022physics.data-an cs.LG hep-excited by 6

Not on the map. Why?

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 78 references that are in the map. First posted on arXiv 25 Mar 2022.

Builds on

18 of 78 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2016Concrete Problems in AI Safetycited by 1,582
  8. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2017One pixel attack for fooling deep neural networkscited by 579
  11. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 438
  12. 2018Adversarial Attacks and Defences: A Surveycited by 259
6 more
  1. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  2. 2016Robustness of classifiers: from adversarial to random noisecited by 87
  3. 2016Learning to Pivot with Adversarial Networkscited by 55
  4. 2015Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimizationcited by 32
  5. 2021DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classificationcited by 10
  6. 2019AI Safety for High Energy Physicscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2023Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surfacecited by 2
  2. 2025MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networkscited by 2
  3. 2024Image and Point-cloud Classification for Jet Analysis in High-Energy Physics: A surveycited by 1
  4. 2022Exploring the Universality of Hadronic Jet Classificationcited by 0
  5. 2024Enhancing generalization in high energy physics using white-box adversarial attackscited by 0
  6. 2026Safe Domain Adaptation for Physics: Overcoming Nuisances, Label Shifts, and Simulation Priorscited by 0