A Theoretical Analysis: Physical Unclonable Functions and the Software Protection Problem

Abstract

Physical Unclonable Functions (PUFs) or Physical One Way Functions (P-OWFs) are physical systems whose responses to input stimuli are easy to measure but hard to clone. The unclonability property is due to the accepted hardness of replicating the multitude of uncontrollable manufacturing characteristics and makes PUFs useful in solving problems such as device authentication, software protection and licensing, and certified execution. In this paper, we investigate the effectiveness of PUFs for software protection in hostile offline settings. We show that traditional non-computational (black-box) PUFs cannot solve the software protection problem in this context. We provide two real-world adversary models (weak and strong variants) and security definitions for each. We propose schemes secure against the weak adversary and show that no scheme is secure against a strong adversary without the use of trusted hardware. Finally, we present a protection scheme secure against strong adversaries based on trusted hardware.