Abstract Adversarial Robustness Distillation (ARD) aims to transfer the robustness of large teacher models to small student models, facilitating the attainment of robust performance on …
Abstract The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at …
The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim towards …
Deep neural networks are vulnerable to adversarial attacks leading to erroneous outputs. Adversarial training has been recognized as one of the most effective methods to counter …
J Zhang, Y Hong, Q Zhao - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Adversarial training is an effective way to defend deep neural networks (DNN) against adversarial examples. However, there are atypical samples that are rare and hard to learn …
F Liu, C Zhang, H Zhang - 2023 IEEE Conference on Secure …, 2023 - ieeexplore.ieee.org
Transfer-based adversarial example is one of the most important classes of black-box attacks. However, there is a trade-off between transferability and imperceptibility of the …
This paper proposes a new loss function for adversarial training. Since adversarial training has difficulties, eg, necessity of high model capacity, focusing on important data points by …
Adversarial training is a popular method to robustify models against adversarial attacks. However, it exhibits much more severe overfitting than training on clean inputs. In this work …
Adversarial training (AT) has proven to be one of the most effective ways to defend Deep Neural Networks (DNNs) against adversarial attacks. However, the phenomenon of robust …