InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle. (arXiv:2206.12292v1 [cs.LG])

Adversarial training (AT) has shown excellent high performance in defending
against adversarial examples. Recent studies demonstrate that examples are not
equally important to the final robustness of models during AT, that is, the
so-called hard examples that can be attacked easily exhibit more influence than
robust examples on the final robustness. Therefore, guaranteeing the robustness
of hard examples is crucial for improving the final robustness of the model.
However, defining effective heuristics to search for hard examples is still
difficult. …

arxiv information lg training