Dataset for: A Deep-Learning Technique to Locate Cryptographic Operations in Side-Channel Traces

This dataset is part of "A Deep-Learning Technique to Locate Cryptographic Operations in Side-Channel Traces" available online.

The source code for testing the dataset is available on GitHub.

The dataset is organized as follows:

• \training: contains three subsets, i.e., train, valid, and test.  
    Each subset consists of two .npy files:
  • _set: it contains the side-channel traces that are preprocessed accordingly.
  •  _labels: itcontains the target labels for training the CNN, labeling each data as cipher start, cipher rest, or noise.
• \inference: contains two files as a demo of the inference pipeline.
      One file is the is the side-channel trace containing an undefined number of AES encryptions. The other file is a list of plaintexts matching the AES encryptions to test a CPA attack.

Cite:

@INPROCEEDINGS{10546758,
   author={Chiari, Giuseppe and Galli, Davide and Lattari, Francesco and Matteucci, Matteo and Zoni, Davide},
   booktitle={2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)}, 
   title={A Deep- Learning Technique to Locate Cryptographic Operations in Side-Channel Traces}, 
   year={2024},
   pages={1-6},
   doi={10.23919/DATE58400.2024.10546758}}

This repository is protected by copyright and licensed under the Creative Commons Attribution 4.0 International license.

© 2024 hardware-fab