Paper
A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets
Deep learning-based side-channel analysis has historically focused on single-byte targets and manually cropped traces, which risks discarding exploitable leakage. While recent work has proposed specialized architectures and resampling techniques to address this gap, the literature lacks a simple transformer baseline for simultaneous full-key attacks on uncropped traces. We present an open-source transformer implement · Authors: Jimmy Gammell, Kaushik Roy · Published 2026-08-31 · arXiv:2608.30105
- Published
- 2026-08-31
- Authors
- 2
- arXiv
- 2608.30105
- Category
- cs.CR
Abstract
arXiv:2608.30105
Jimmy Gammell, Kaushik Roy
Deep learning-based side-channel analysis has historically focused on single-byte targets and manually cropped traces, which risks discarding exploitable leakage. While recent work has proposed specialized architectures and resampling techniques to address this gap, the literature lacks a simple transformer baseline for simultaneous full-key attacks on uncropped traces. We present an open-source transformer implementation for uncropped full-key attacks which uses the standard transformer encoder backbone, adapting only the input and output layers to the side-channel setting. We release our implementation, training recipes, and pretrained weights for uncropped ASCADv1f, ASCADv1r, and CHES-CTF-2018 which achieve performance competitive with previously-reported results, while using less than 10GB of VRAM and requiring at most 3.34 hours of training on a single NVIDIA A6000.