Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems
arXiv:2204.09514 · doi:10.1109/VTS52500.2021.9794253
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 real-world 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.
Appears at 40th IEEE VLSI Test Symposium (VTS 2022), 14 pages
References in corpus (6)
- Stealing Machine Learning Models via Prediction APIs
- Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
- Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead
- Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
- A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators
- Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters