AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance
This addresses reliability issues for safety-critical applications by improving multiple robustness without harming generalization, though it appears incremental as it builds on adversarial training methods.
The paper tackles the problem of deep neural networks sacrificing generalization or other robustness aspects when improving specific robustness, proposing AugRmixAT to simultaneously enhance generalization and multiple robustness types, with experiments on CIFAR-10/100 and Tiny-ImageNet showing improvements in white-box, black-box, common corruption, and partial occlusion robustness.
Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial for their application in safety-critical areas. Much previous work has been proposed to improve specific robustness. However, we find that the specific robustness is often improved at the sacrifice of the additional robustness or generalization ability of the neural network model. In particular, adversarial training methods significantly hurt the generalization performance on unperturbed data when improving adversarial robustness. In this paper, we propose a new data processing and training method, called AugRmixAT, which can simultaneously improve the generalization ability and multiple robustness of neural network models. Finally, we validate the effectiveness of AugRmixAT on the CIFAR-10/100 and Tiny-ImageNet datasets. The experiments demonstrate that AugRmixAT can improve the model's generalization performance while enhancing the white-box robustness, black-box robustness, common corruption robustness, and partial occlusion robustness.