Improving Robustness of Jet Tagging Algorithms with Adversarial Training

Abstract

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.

17 pages, 16 figures, 2 tables. Replaced with the published version. Added the journal reference and the DOI. Code accessible under https://github.com/AnnikaStein/Adversarial-Training-for-Jet-Tagging

References in corpus (6)

• PYTHIA 6.4 Physics and Manual
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Measurement of the $c$-jet mistagging efficiency in $t\bar{t}$ events using $pp$ collision data at $\sqrt{s}=13$ TeV collected with the ATLAS detector
• Uncertainty Aware Learning for High Energy Physics
• A new calibration method for charm jet identification validated with proton-proton collision events at $\sqrt{s}$ = 13 TeV
• Adversarial methods to reduce simulation bias in neutrino interaction event filtering at Liquid Argon Time Projection Chambers

Cited by in corpus (3)

• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Accuracy versus precision in boosted top tagging with the ATLAS detector
• Enhancing generalization in high energy physics using white-box adversarial attacks