Robust NAS under adversarial training: benchmark, theory, and beyond
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 networks from the NAS-Bench-201 search space on image datasets. Then, leveraging the neural tangent kernel (NTK) tool from deep learning theory, we establish a generalization theory for searching architecture in terms of clean accuracy and robust accuracy under multi-objective adversarial training. We firmly believe that our benchmark and theoretical insights will significantly benefit the NAS community through reliable reproducibility, efficient assessment, and theoretical foundation, particularly in the pursuit of robust architectures.
Code (0)
등록된 구현이 없습니다.
Tasks
Learning TheoryNeural Architecture SearchMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarially Robust Estimate and Risk Analysis in Linear Regression
Adversarially robust learning aims to design algorithms that are robust to small adversarial perturbations on input variables. Beyond the existing studies on the predictive performance to adversarial samples, our goal is…
Adversarial Robustnessregression$\ell_\infty$-Robustness and Beyond: Unleashing Efficient Adversarial Training
Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches in training rob…
Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts. Most UDA approaches emphasize transfer ability, but often overloo…
Unsupervised Domain AdaptationAdversarial RobustnessDeepKnowledge: Generalisation-Driven Deep Learning Testing
Despite their unprecedented success, DNNs are notoriously fragile to small shifts in data distribution, demanding effective testing techniques that can assess their dependability. Despite recent advances in DNN testing, …
Deep LearningDNN TestingPower up! Robust Graph Convolutional Network via Graph Powering
Graph convolutional networks (GCNs) are powerful tools for graph-structured data. However, they have been recently shown to be vulnerable to topological attacks. To enhance adversarial robustness, we go beyond spectral g…
Adversarial Robustness