PUF Phenotype CNN-based Authentication Experimental Code and ML Models

The following code and ML models will allow you to recreate/modify the experimental work undertaken in Chapter 3 of the PhD thesis ' Leveraging DRAM-based Physically Unclonable Functions for Enhancing Authentication in Resource-Constrained Applications' by Owen Millwood (and the key publication [1]).

It includes the trained VGG16 (with and without classification layer) models and trained classical ML classifiers from the work directly.

Also included is the code which can be modified or executed however you like.

The dataset compatible with this code can be found using the following DOI: 10.15131/shef.data.26977528

[1] O. Millwood, J. Miskelly, B. Yang, P. Gope, E. B. Kavun and C. Lin, "PUF-Phenotype: A Robust and Noise-Resilient Approach to Aid Group-Based Authentication With DRAM-PUFs Using Machine Learning," in IEEE Transactions on Information Forensics and Security, vol. 18, pp. 2451-2465, 2023, doi: 10.1109/TIFS.2023.3266624.