
Label refinement in adversarial training mitigates robust overfitting by addressing noisy labels.


coremsg

addressing-robustness-in-adversarial-training-with-self-guided-label-refinement


Addressing Robustness in Adversarial Training with Self-Guided Label Refinement


title_rewrite


This paper introduces a novel approach called Robustness Reprogramming, which enhances the robustness of pre-trained deep learning models against adversarial attacks without modifying their original parameters, achieving this by replacing the traditional linear feature transformation with a robust non-linear pattern matching technique.


reprogramming-pre-trained-deep-learning-models-for-enhanced-robustness-against-adversarial-attacks-


Reprogramming Pre-trained Deep Learning Models for Enhanced Robustness Against Adversarial Attacks
