Metraipolis › archive › dc_0e32faef37e0

A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets — arXiv:2608.30105

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30105
License (as archived)
CC0-1.0
Archived
2026-10-17T08:25:45.400Z
SHA-256 of the archived text
7c80d386b87ba64c0a97f7a7b3a15cbf90f75eb93df671aa9cb8d14dce0e90a1
Stable URL of this page
https://metraipolis.com/documento/dc_0e32faef37e0

How to cite

A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets — arXiv:2608.30105 — arXiv (en), https://arxiv.org/abs/2608.30105 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0e32faef37e0 (Metraipolis archive dc_0e32faef37e0, sha256 7c80d386b87ba64c0a97f7a7b3a15cbf90f75eb93df671aa9cb8d14dce0e90a1)
BibTeX
@misc{dc0e32faef37e0,
  title = {A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets — arXiv:2608.30105},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30105},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0e32faef37e0; sha256 7c80d386b87ba64c0a97f7a7b3a15cbf90f75eb93df671aa9cb8d14dce0e90a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30105. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.30105 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T08:10:59.881Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).