Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems

Abstract

The real-world use cases of Machine Learning (ML) have exploded over the past few years. However, the current computing infrastructure is insufficient to support all realworld applications and scenarios. Apart from high efficiency requirements, modern ML systems are expected to be highly reliable against hardware failures as well as secure against adversarial and IP stealing attacks. Privacy concerns are also becoming a first-order issue. This article summarizes the main challenges in agile development of efficient, reliable and secure ML systems, and then presents an outline of an agile design methodology to generate efficient, reliable and secure ML systems based on user-defined constraints and objectives.

RoHNAS: A Neural Architecture Search Framework With Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks

“…Such a threat is extremely dangerous for safety-critical applications [7]. Furthermore, integrating means for security during NAS is a challenging problem, but can enable robust DNN designs [8] [9], as compared to the regular DNN design flow. Hence, the problem is: how to design complex DNNs in an energy-efficient and robust way through an automated multiobjective NAS framework?…”