Improving Adversarial Robustness via Feature Pattern Consistency Constraint

arXiv:2406.08829v1 Announce Type: cross
Abstract: Convolutional Neural Networks (CNNs) are well-known for their vulnerability to adversarial attacks, posing significant security concerns. In response to these threats, various defense methods have emerged to bolster the model's robustness. However, most existing methods either focus on learning from adversarial perturbations, leading to overfitting to the adversarial examples, or aim to eliminate such perturbations during inference, inevitably increasing computational burdens. Conversely, clean training, which strengthens the model's robustness by relying solely on clean examples, …

adversarial adversarial attacks arxiv attacks bolster cnns consistency convolutional neural networks cs.cr cs.cv defense feature focus networks neural networks response robustness security security concerns threats vulnerability well-known