The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations


  • Stjepan Picek Delft University of Technology, Delft, The Netherlands; LAGA, Department of Mathematics, University of Paris 8 (and Paris 13 and CNRS)
  • Annelie Heuser Univ Rennes, Inria, CNRS, IRISA
  • Alan Jovic University of Zagreb Faculty of Electrical Engineering and Computing
  • Shivam Bhasin Physical Analysis and Cryptographic Engineering, Temasek Laboratories at Nanyang Technological University
  • Francesco Regazzoni University of Lugano



Profiled side-channel attacks, Imbalanced datasets, Synthetic examples, SMOTE, Metrics


We concentrate on machine learning techniques used for profiled sidechannel analysis in the presence of imbalanced data. Such scenarios are realistic and often occurring, for instance in the Hamming weight or Hamming distance leakage models. In order to deal with the imbalanced data, we use various balancing techniques and we show that most of them help in mounting successful attacks when the data is highly imbalanced. Especially, the results with the SMOTE technique are encouraging, since we observe some scenarios where it reduces the number of necessary measurements more than 8 times. Next, we provide extensive results on comparison of machine learning and side-channel metrics, where we show that machine learning metrics (and especially accuracy as the most often used one) can be extremely deceptive. This finding opens a need to revisit the previous works and their results in order to properly assess the performance of machine learning in side-channel analysis.



How to Cite

Picek, S., Heuser, A., Jovic, A., Bhasin, S., & Regazzoni, F. (2018). The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations. IACR Transactions on Cryptographic Hardware and Embedded Systems, 2019(1), 209–237.