Robust NAS under adversarial training: benchmark, theory, and beyond

arXiv:2403.13134v1 Announce Type: new
Abstract: Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robust architectures, especially when adversarial training is considered. In this work, we aim to address these two challenges, making twofold contributions. First, we release a comprehensive data set that encompasses both clean accuracy and robust accuracy for a vast array of adversarially trained …

abstract adversarial adversarial training aim architecture architectures arxiv benchmark beyond cs.ai cs.lg data however nas neural architecture search robust search searching significance stat.ml theory training type work