Accurate and Robust Neural Architecture Search via a Flexible Supernet

Neural architecture search (NAS, the automated process of designing AI model structures) can produce models that are vulnerable to adversarial attacks (manipulated inputs designed to fool AI systems). This paper presents ARNAS++, a method that searches for neural architectures that are both accurate and robust against adversarial attacks by using a flexible supernet (a large parent network from which smaller networks are derived) with adjustable parameter budgets and width.