Sub-Space Modeling: An Enrollment Solution for XOR Arbiter PUF using Machine Learning

Summary form only given. In this work we present sub-space modeling of XOR Arbiter PUF as a cost efficient solution for enrollment for the designers’ community. Our goal is to demonstrate a method which can reduce the overall cost in terms of number of CRPs required for training, training time and memory. Here we propose to reduce the complexity of the modeling target by dividing the PUF into smaller sub-components and model each sub-component of the PUF independently. Our early experimental assessment show that our sub-space modeling can significantly reduce the cost of training compared to some of the latest works, thus it is potentially a cost-efficient solution to enroll strong PUF with high complexity.