TY - DATA T1 - Code underlying the publication: Autoencoder-enabled model portability for reducing hyperparameter tuning efforts in side-channel analysis PY - 2024/05/14 AU - Marina KrĨek UR - DO - 10.4121/fe14a263-d5f1-4d3e-8d06-b1be95904acf.v1 KW - Side-channel Analysis KW - Autoencoders KW - Preprocessing KW - Hyperparameter Tuning KW - Portability KW - Transfer Learning N2 -
Link to GitHub repository with source code for the publication: Autoencoder-enabled model portability for reducing hyperparameter tuning efforts in side-channel analysis.
The source code uses the Python programming language. Scripts used to run the experiments are in the main directory, while the folder 'src' holds the implementations for hyperparameter tuning, loading of side-channel datasets, etc., providing some abstraction. Scripts starting with 'attack' were used to run experiments, while other scripts were helper scripts for analyzing/reading/plotting results.
Sbatch scripts were used to run experiments with TU Delft servers.
More information can be found in the publication.
ER -