<ul><li>Adversarial training (AT) is an effective technique for enhancing adversarial robustness, but it usually comes at the cost of a decline in generalization ability.</li><li>Recent studies have attempted to use clean training to assist adversarial training, yet there are contradictions among the conclusions.</li><li>The knowledge combinations transferred from clean-trained models to adversarially-trained models can be divided into two categories: reducing the learning difficulty and providing correct guidance.</li><li>By leveraging clean training, the performance of advanced AT methods can be further improved, and the problem of generalization degradation faced by AT can be alleviated.</li></ul>

Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better

Discover more