SunRISE (SunRISE)

Themes: Electronic Systems and VLSI Design

Implement machine learning on encrypted data to improve security aspects of smart IoT devices

SunRISE proposes a shared security solution to tackle the security aspects of smart IoT devices: Implement ML on the edge nodes enabling IoT security analytics to defend against intrusion attacks or detect misconfigurations. Share security relevant data of several companies via a cloud platform and apply ML techniques also on the combined data and models. Evaluate homomorphic encryption as a privacy enhancing technology and apply ML algorithms on combined encrypted data sets.

To obtain a comprehensive security solution, SunRISE addresses several key aspects, critical in future IoT systems. First, design intrusion detection, by using the latest novel results in machine learning to address security anomaly detection aspects. Second, sharing of security intelligence data from IoT nodes to cloud backends, by creating a community with reference structures. Based on the larger dataset, machine learning can be accelerated and overall system security increased. This would result in security turning into a shared responsibility, interest and effort, and into improved efficiency, cost and resource usage. Third, the lack of trust by fearing the loss of confidential data will be addressed by using privacy-enhancing technologies (PET), like homomorphic encryption and secure multi-party computation (MPC). Last, the efficient, power and cost-effective introduction of PET will be addressed by designing and manufacturing suitable hardware supporting AI specific to IoT end-nodes and for acceleration.

Project data

Starting date: September 2019
Closing date: December 2021
Sponsor: Penta
Contact: René van Leuken