Fundamentals of AI

The working group collected the following pointers as a starting point for new researchers and practitioners in the field of AI for implementation security.

• Machine Learning Networks
  • Andrew Ng's Machine Learning (Coursera) — Lectures 1–3
  • Survey on using ML for SCA
• Training and Testing
  • Practice Template Attacks
  • Practice Profiling Attacks with Neural Networks
• Tools
  • PyTorch
  • Keras and SciKit
  • JAX/Flax
  • Code to start with:
    • https://github.com/pace-tl-ntu/Pytorch_Baseline_DLSCA (Single DNN)
    • https://github.com/pace-tl-ntu/Pytorch_Baseline_Ensemble_DLSCA (Ensemble DNNs)
    • https://github.com/AISyLab/AISY_Framework
    • https://github.com/ANSSI-FR/ASCAD
    • GPAM and sedpack tutorials:
      • https://google.github.io/sedpack/tutorials/sca/dataset/
      • https://google.github.io/sedpack/tutorials/sca/gpam/
• Hyperparameter Search Methods
  • SciKit based hyperparameter tuning
  • Keras Tuner

Additional References

• L. Masure, C. Dumas, and E. Prouff, "A comprehensive study of deep learning for side-channel analysis," IACR Trans. Cryptogr. Hardw. Embed. Syst., vol. 2020, no. 1, pp. 348–375, 2019, doi: 10.13154/tches.v2020.i1.348-375.
• G. Perin, Ł. Chmielewski, and S. Picek, "Strength in numbers: Improving generalization with ensembles in machine learning-based profiled side-channel analysis," IACR Trans. Cryptogr. Hardw. Embed. Syst., vol. 2020, no. 4, pp. 337–364, 2020, doi: 10.13154/tches.v2020.i4.337-364.
• L. Wouters, V. Arribas, B. Gierlichs, and B. Preneel, "Revisiting a methodology for efficient CNN architectures in profiling attacks," IACR Trans. Cryptogr. Hardw. Embed. Syst., vol. 2020, no. 3, pp. 147–168, 2020, doi: 10.13154/tches.v2020.i3.147-168.
• J. Rijsdijk, L. Wu, G. Perin, and S. Picek, "Reinforcement learning for hyperparameter tuning in deep learning-based side-channel analysis," IACR Trans. Cryptogr. Hardw. Embed. Syst., vol. 2021, no. 3, pp. 677–707, 2021, doi:10.46586/tches.v2021.i3.677-707
• L. Wu, G. Perin, and S. Picek, "I choose you: Automated hyperparameter tuning for deep learning-based side-channel analysis," IEEE Trans. Emerg. Top. Comput., early access, 2022, doi: 10.1109/TETC.2022.3218372.
• R. Y. Acharya, F. Ganji, and D. Forte, "Information theory-based evolution of neural networks for side-channel analysis," IACR Trans. Cryptogr. Hardw. Embed. Syst., vol. 2023, no. 1, pp. 401–437, 2023, doi: 10.46586/tches.v2023.i1.401-437