Improving Robustness of Jet Tagging Algorithms with Adversarial Training
This addresses robustness issues in jet flavor tagging for high-energy physics, though it is incremental as it builds on existing adversarial training methods.
The paper tackled the problem of deep learning jet tagging algorithms being vulnerable to mismodeling in simulations by investigating adversarial attacks and proposing an adversarial training strategy, which improved classifier robustness and reduced vulnerability to poor modeling.
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.