Security Analysis of Machine Learning-Based PUF Enrollment Protocols: A Review

Abstract

The demand for Internet of Things services is increasing exponentially, and consequently a large number of devices are being deployed. To efficiently authenticate these objects, the use of physical unclonable functions (PUFs) has been introduced as a promising solution for the resource-constrained nature of these devices. The use of machine learning PUF models has been recently proposed to authenticate the IoT objects while reducing the storage space requirement for each device. Nonetheless, the use of a mathematically clonable PUFs requires careful design of the enrollment process. Furthermore, the secrecy of the machine learning models used for PUFs and the scenario of leakage of sensitive information to an adversary due to an insider threat within the organization have not been discussed. In this paper, we review the state-of-the-art model-based PUF enrollment protocols. We identity two architectures of enrollment protocols based on the participating entities and the building blocks that are relevant to the security of the authentication procedure. In addition, we discuss their respective weaknesses with respect to insider and outsider threats. Our work serves as a comprehensive overview of the ML PUF-based methods and provides design guidelines for future enrollment protocol designers.

Ultrafast Near‐Ideal Phase‐Change Memristive Physical Unclonable Functions Driven by Amorphous State Variations

“…[ 29 , 30 ] A secret challenge‐response pair (CRP) space that is known only to a verifier results from modeling PUF as a mathematical function that maps the inputs/challenges ( c ) to outputs/responses ( r ), viz., ( r = f ( c )). [ 31 , 32 ] Depending on whether the number of CRPs are linearly or supra‐linearly related to the number of physical random elements in the circuit, the PUF is grouped as weak PUF or strong PUF. [ 33 , 34 ] Strong PUF are harnessed for applications such as authentication which requires the creation of multiple keys, whereas weak PUF are utilized for hardware identification.…”

FPGA Implementation of Secure Protocol for Hardware Authentication and Activation

“…The use of a PUF is advantageous in preventing overproduction by assigning a unique activation code during the enrollment [8]. This code generates device-specific keys and enables server monitoring to prevent unauthorized devices from infiltrating the market [8]. The following section will detail the construction of the PUF and its use as a cryptographic root key.…”