Abstract:
Tiny machine learning (TinyML) is an essential component of emerging smart microcontrollers (MCUs). However, the protection of the intellectual property (IP) of the model...Show MoreMetadata
Abstract:
Tiny machine learning (TinyML) is an essential component of emerging smart microcontrollers (MCUs). However, the protection of the intellectual property (IP) of the model is an increasing concern due to the lack of desktop/server-grade resources on these power-constrained devices. In this paper, we propose STML, a system and algorithm co-design to Secure IP of TinyML on MCUs with ARM TrustZone. Our design jointly optimizes memory utilization and latency while ensuring the security and accuracy of emerging models. We implemented a prototype and benchmarked with 7 models, demonstrating STML reduces 40% of model protection runtime overhead on average.
Published in: 2023 60th ACM/IEEE Design Automation Conference (DAC)
Date of Conference: 09-13 July 2023
Date Added to IEEE Xplore: 15 September 2023
ISBN Information: