A comparative study shows CNNs, ResNets, and feature-selected Random Forests can recover an AES key byte from ASCAD EM traces despite near-zero classification accuracy, when evaluated with the domain-specific Key Rank metric.
Journal of Cryptographic Engineering 10(2), 163–188 (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine Learning-Based AES Key Recovery via Side-Channel Analysis on the ASCAD Dataset
A comparative study shows CNNs, ResNets, and feature-selected Random Forests can recover an AES key byte from ASCAD EM traces despite near-zero classification accuracy, when evaluated with the domain-specific Key Rank metric.