Searching for Robust Neural Architectures via Comprehensive and Reliable Evaluation
share
Neural architecture search (NAS) could help search for robust network architectures, where defining robustness evaluation metrics is the important procedure. However, current robustness evaluations in NAS are not sufficiently comprehensive and reliable. In particular, the common practice only considers adversarial noise and quantified metrics such as the Jacobian matrix, whereas, some studies indicated that the models are also vulnerable to other types of noises such as natural noise. In addition, existing methods taking adversarial noise as the evaluation just use the robust accuracy of the FGSM or PGD, but these adversarial attacks could not provide the adequately reliable evaluation, leading to the vulnerability of the models under stronger attacks. To alleviate the above problems, we propose a novel framework, called Auto Adversarial Attack and Defense (AAAD), where we employ neural architecture search methods, and four types of robustness evaluations are considered, including adversarial noise, natural noise, system noise and quantified metrics, thereby assisting in finding more robust architectures. Also, among the adversarial noise, we use the composite adversarial attack obtained by random search as the new metric to evaluate the robustness of the model architectures. The empirical results on the CIFAR10 dataset show that the searched efficient attack could help find more robust architectures.
READ FULL TEXT