Generative model improves hardware portability of deep learning side-channel analysis
s-MDM: Generative Virtualization of Multi-Device Hardware Variations for Portable DL-SCA
Cryptography and Security
Summary
Deep learning methods that analyze hardware to find secret information often fail when tested on new devices because of subtle differences in hardware. The authors created a new generative model called s-MDM that creates virtual device profiles to train such methods without needing data from the new devices. Their model works well on different hardware setups where traditional methods struggle or fail. This approach helps make deep learning side-channel analysis more reliable and portable across various devices.
What this means in practice
- •For hardware security teams: Improve side-channel attack models to work reliably across different device variants without collecting new device data.
- •For embedded system developers: Generate synthetic device profiles to better test cryptographic hardware resistance against side-channel attacks before deployment.
Authors
Niloufar Sayadi, Marten van Dijk, Chenglu Jin
Abstract
Deep Learning-based Side-Channel Analysis (DL-SCA) frequently suffers from catastrophic performance degradation across unseen hardware due to printed circuit board routing differences, silicon process variations, and measurement noise shifts. This poster presents the Synthetic Multiple Device Model (s-MDM), a zero-target-trace generative framework designed to improve cross-device portability. s-MDM combines a structured cVAE generator, a Walsh-Hadamard leakage anchor, continuous style modulation, and decoupled leakage-style--domain critics to synthesize virtual source-device profiles offline. Benchmarked on 32-bit side-channel traces (AES_PTv2), s-MDM maps a precise operational boundary: while physical MDM remains superior on identical electrical clones (D4), s-MDM achieves consistently low key rank on the layout/acquisition-shifted Pinata target, where physical baselines are unstable or misaligned.