GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks. (arXiv:2302.02907v2 [cs.CV] UPDATED)

While leveraging additional training data is well established to improve
adversarial robustness, it incurs the unavoidable cost of data collection and
the heavy computation to train models. To mitigate the costs, we propose Guided
Adversarial Training (GAT), a novel adversarial training technique that
exploits auxiliary tasks under a limited set of training data. Our approach
extends single-task models into multi-task models during the min-max
optimization of adversarial training, and drives the loss optimization with a
regularization of the gradient curvature …

adversarial collection computation cost data data collection exploits novel robustness train training under