Abstract—Accelerators used for machine learning (ML) inference provide great performance benefits over CPUs. Securing confidential model in inference against off-chip side-channel attacks is critical ...

A technical paper titled “Hardware-Software Co-design for Side-Channel Protected Neural Network Inference” was published (preprint) by researchers at North Carolina State University and Intel.

A team of North Carolina State University researchers recently published a paper that highlights the vulnerability of machine learning (ML) models to side-channel attacks. Specifically, the team used ...