AUTHOR=Li Yize , Zhao Pu , Ding Ruyi , Zhou Tong , Fei Yunsi , Xu Xiaolin , Lin Xue 

TITLE=Neural architecture search for adversarial robustness via learnable pruning

JOURNAL=Frontiers in High Performance Computing

VOLUME=Volume 2 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/high-performance-computing/articles/10.3389/fhpcp.2024.1301384

DOI=10.3389/fhpcp.2024.1301384

ISSN=2813-7337

ABSTRACT=The convincing performances of deep neural networks (DNNs) can be degraded tremendously under malicious samples, known as adversarial examples. Besides, with the widespread edge platforms, it is essential to reduce the DNN model size for efficient deployment on resourcelimited edge devices. To achieve both adversarial robustness and model sparsity, we propose a robustness-aware search framework, an Adversarial Neural Architecture Search by the Pruning policy (ANAS-P). The layer-wise width is searched automatically via the binary convolutional mask, titled Depth-wise Differentiable Binary Convolutional indicator (D2BC). By conducting comprehensive experiments on three classification datasets (CIFAR-10, CIFAR-100, and Tiny-ImageNet) utilizing two adversarial losses (TRADES and MART), we empirically demonstrate the effectiveness of ANAS in terms of clean accuracy and adversarial robust accuracy across various sparsity levels. Our proposed approach, ANAS-P, outperforms previous representative methods, especially in high-sparsity settings with significant improvements.