PhD in Trusted Virtualization Architectures for Confidential AI

The Inria Rennes - Bretagne Atlantique Centre is seeking a PhD student to work on trusted virtualization architectures for confidential AI. The project, funded by the CUPSELI Inria Challenge, aims to investigate how server-side confidential-computing technologies can be used to secure training and inference in decentralized machine-learning systems. The PhD student will be hosted by the WIDE team in Rennes and jointly supervised by researchers from WIDE and members of Hivenet in Cannes. The research will involve designing new virtualization mechanisms and a trusted Virtual Machine Monitor (VMM) for confidential AI workloads, with a focus on systems contributions at the intersection of operating systems, virtualization, distributed systems, and hardware-assisted security. The ideal candidate should have excellent programming skills, including solid experience with low-level systems programming, and be willing to learn and work with new technologies and techniques in areas such as confidential computing, virtualization, trusted execution environments, and machine learning.

• Design and implement a trusted Virtual Machine Monitor (VMM) for confidential AI workloads
• Investigate new mechanisms to address the first research challenge: enabling the VMM to provide security services transparently to the guest operating system
• Explore hybrid architectures that combine confidential-computing-enabled devices with untrusted or incompatible resources
• Integrate the results of the previous phases into a scalable and reusable VMM architecture
• Evaluate the resulting prototype on representative machine-learning workloads