Active learning for fast and slow modeling attacks on Arbiter PUFs

TL;DR

This paper explores active learning strategies to improve the efficiency of modeling attacks on Arbiter PUFs by selecting challenges that accelerate or hinder the learning process, impacting both attackers and defenders.

Contribution

It introduces challenge construction methods for active learning in SVM-based PUF modeling, enabling faster or slower learning compared to prior sample pool approaches.

Findings

Active learning reduces CRPs needed for high-accuracy modeling.

Challenge selection can accelerate or slow down the learning process.

Methods can aid manufacturers or attackers depending on the context.

Abstract

Modeling attacks, in which an adversary uses machine learning techniques to model a hardware-based Physically Unclonable Function (PUF) pose a great threat to the viability of these hardware security primitives. In most modeling attacks, a random subset of challenge-response-pairs (CRPs) are used as the labeled data for the machine learning algorithm. Here, for the arbiter-PUF, a delay based PUF which may be viewed as a linear threshold function with random weights (due to manufacturing imperfections), we investigate the role of active learning in Support Vector Machine (SVM) learning. We focus on challenge selection to help SVM algorithm learn ``fast'' and learn ``slow''. Our methods construct challenges rather than relying on a sample pool of challenges as in prior work. Using active learning to learn ``fast'' (less CRPs revealed, higher accuracies) may help manufacturers learn the manufactured PUFs more efficiently, or may form a more powerful attack when the attacker may query the PUF for CRPs at will. Using active learning to select challenges from which learning is ``slow'' (low accuracy despite a large number of revealed CRPs) may provide a basis for slowing down attackers who are limited to overhearing CRPs.