Sowrya Gali

Adversarial Robustness without Adversarial Training: A Teacher-Guided Curriculum Learning Approach

Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps. Being repetitive in nature during the inner maximization step, they take a huge time to train. We propose a non-iterat…