loading page

Security Analysis of Digital-Based Physically Unclonable Functions: Dataset Generation, Machine Learning Modeling, and Correlation Analysis
  • +3
  • Enas Abulibdeh,
  • Shimaa Naser,
  • Hani Saleh,
  • Baker Mohammad,
  • Mahmoud Al-Qutayri,
  • Sami Muhaidat
Enas Abulibdeh

Corresponding Author:[email protected]

Author Profile
Shimaa Naser
Hani Saleh
Baker Mohammad
Mahmoud Al-Qutayri
Sami Muhaidat


Physically unclonable functions (PUFs) are circuit primitives that offer a promising and cost-effective solution for various security applications, such as integrated circuits (IC) counterfeiting, secret key generation, and lightweight authentication. PUFs leverage semiconducting variations of ICs to extract intrinsic responses based on applied challenges, establishing unique challenge-response pairs (CRPs) for each device. The security analysis of PUFs is crucial to identify the device weaknesses and ensure response integrity. Accordingly, CRP-based examination plays a major role in defining the resistivity of the block against general and modeling-based attacks. Such analysis requires an updated and representative dataset for training and evaluation. However, there is a lack of benchmark datasets for assessing the effectiveness and resistance of PUF devices. Motivated by this, in this work, we generate a dataset of 300K CRPs for a digital-based PUF implemented on a field programmable gate array (FPGA). The dataset provides a significant number of CRPs for a multi-bit response, where the spatial and temporal adjacency are implicitly defined in the extracted CRPs. Moreover, we investigate different approaches utilizing the generated dataset such as machine learning-based modeling, correlation analysis, and entropy analysis. The CRPs are employed to train linear and nonlinear Support Vector Machine (SVM) models, and the prediction accuracy of SVM models is used as an indicator of the PUF's vulnerability to modeling attacks. As the prediction accuracy does not exceed 65% over 10K CRPs, the extracted dataset sufficiently verifies the resiliency of the device against ML-based modeling attacks. Additionally, Pearson's coefficient is computed on a 10 K-bit vector to determine the correlation between the bits of the response. The calculations expose some correlations between ±0.25, which warns from potential threads. Finally, the paper discusses some potential future research directions and challenges that are envisioned to enhance the security performance of PUFs.
18 Mar 2024Submitted to TechRxiv
29 Mar 2024Published in TechRxiv