Federated Learning with Low Resources
This project aims to develop Software-Defined IoT building blocks for a deeply embedded software platform fitting low-power devices, architectured for privacy-by-design and cybersecurity. The goal is to provide capabilities to isolate small runtime containers of untrusted (possibly scripted) IoT logic, and adequate privacy-oriented preprocessing (such as differential privacy and lightweight cryptographic tools) of IoT data on-board, before it is transferred from the OS to the container(s) and/or from the containers to the cloud. Thus we explore tradeoffs between isolation guarantees, the logic orchestration functionality & security, memory footprint and ease of use by non-specialist embedded systems developer. In practice, the project is based its embedded development on the open source operating system RIOT and the protokernel PIP.
The project website is here: https://tinypart.github.io/TinyPART/