Model theft attack against a tinyML application running on an Ultra-Low-Power Open-Source SoC

With the advent of tinyML, IoT devices have expanded their range of operations from simple data gathering and transmission to full-fledged inference. This expansion has been further enabled by the rise in popularity of open-source hardware, with the RISC-V architecture being the most prominent example. TinyML’s decentralization can solve the current privacy and security issues of IoT infrastructures. However, it also shifts the burden of security on already resource-constrained devices. Ultra-low-power devices, in particular, often sacrifice security features for energy and area efficiency. This work aims at showing that, in the context of edge computing based on open-source hardware, neglecting hardware security features for the sake of efficiency is not an acceptable trade-off with respect to AI security.