Published September 5, 2025 | Version v1.2
Dataset Open

Avengers assemble! Supervised learning meets lattice reduction -- A single power trace attack against CRYSTALS-Kyber Key Generation

Authors/Creators

  • 1. ROR icon Université de Rennes
  • 2. IDEMIA
  • 3. ROR icon PQShield (United Kingdom)

Description

Power traces, models and additional data related to the article accepted at CHES 2025 (4th issue) :

Avengers assemble! Supervised learning meets lattice reduction -- A single power trace attack against CRYSTALS-Kyber Key Generation
Pierre-Alain Fouque1, Damien Marion1 , Quyen Nguyen2 Alexandre Wallet3

1Univ Rennes, CNRS, Inria, IRISA, Rennes, France {pierre-alain.fouque,damien.marion}@irisa.fr
2IDEMIA Secure Transactions, Courbevoie, France, thi.nguyen@idemia.com
3PQShield Ltd., Oxford, United Kingdom, alexandre.wallet@pqshield.com

Files

Files (10.9 GB)

Name Size
md5:606ea25e5f3e56abd4c0af91cd3952b6
10.8 GB Download
md5:79c558f18e3fe3be510a9c5a2d6f7343
82.0 MB Download
md5:f4f1f6643eafe9eb3b61b3d644ecf14c
27.2 MB Download
md5:34a80dbf94038106c1212a1ebc888e04
2.7 MB Download

Additional details

Funding

Agence Nationale de la Recherche
IDROMEL - Improving the Design of secure systems by a Reduction Of Micro-architectural Effects on side-channeL attacks ANR-20-CE39-0010

Dates

Submitted
2025-07-28

Software

Repository URL
https://gitlab.inria.fr/capsule/avengers-assemble
Programming language
Python , Sage