Skip to Main content Skip to Navigation
Journal articles

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

Abstract : We concentrate on machine learning techniques used for profiled side-channel 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.
Document type :
Journal articles
Complete list of metadata

Cited literature [46 references]  Display  Hide  Download

https://hal.inria.fr/hal-01935318
Contributor : Annelie Heuser <>
Submitted on : Monday, November 26, 2018 - 3:57:35 PM
Last modification on : Tuesday, September 21, 2021 - 2:16:03 PM
Long-term archiving on: : Wednesday, February 27, 2019 - 2:38:13 PM

File

document-2.pdf
Files produced by the author(s)

Identifiers

Citation

Stjepan Picek, Annelie Heuser, Alan Jovic, Shivam Bhasin, Francesco Regazzoni. The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations. IACR Transactions on Cryptographic Hardware and Embedded Systems, IACR, 2019, 2019 (1), pp.1-29. ⟨10.13154/tches.v2019.i1.209-237⟩. ⟨hal-01935318⟩

Share

Metrics

Record views

917

Files downloads

1282