IP Protection in TinyML | IEEE Conference Publication | IEEE Xplore

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 More

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.
Date of Conference: 09-13 July 2023
Date Added to IEEE Xplore: 15 September 2023
ISBN Information:
Conference Location: San Francisco, CA, USA

References

References is not available for this document.