tinyML Talks: Standardized AI Architectures for Secure TinyML

"Standardized AI Architectures for Secure TinyML"

Andrea Basso
Swiss Federal Institute of Technology, EPFL CH and Stanford Univ. USA

Research director
Synesthesia

Advisor
Progress Tech Transfer Fund

Recently, ML tasks that have been traditionally associated with high-performance CPUs and GPUs, have started to be performed also on highly constrained devices at the far edge. This shift towards the devices, often named TinyML, has many well recognized advantages such as lower bandwidth requirements and energy consumption, cheaper prices, increased privacy, and scalability. However, it also poses serious challenges: first of all, it requires to handle even complex ML tasks with Microcontollers (MCUs) equipped with small memories, low-performance processors, and limited power supply; moreover, TinyML has to face the additional security threats that can specifically affect small devices, that usually have to rely on less support from the hardware and the OS to implement security, and once deployed in the field, can be exposed to physical threats. The MPAI-AIF framework also IEEE P3301 standard produced by the MPAI community, and the IEEE P3301 Artificial Intelligence Framework Working Group described in the talk provides some answers and support to easy implementation of TinyML on MCU.

Видео tinyML Talks: Standardized AI Architectures for Secure TinyML канала tinyML Foundation