SALSA: Attacking Lattice Cryptography with Transformers

Emily Wenger, Mingjie Chen, François Charton, Kristin Lauter
7/11/2022
cs.CRcs.LG

No official code found. Best implementation: facebookresearch/SALSA (29 stars, last commit 2022-11-22).

Abstract

Currently deployed public-key cryptosystems will be vulnerable to attacks by full-scale quantum computers. Consequently, "quantum resistant" cryptosystems are in high demand, and lattice-based cryptosystems, based on a hard problem known as Learning With Errors (LWE), have emerged as strong contenders for standardization. In this work, we train transformers to perform modular arithmetic and combine half-trained models with statistical cryptanalysis techniques to propose SALSA: a machine learning attack on LWE-based cryptographic schemes. SALSA can fully recover secrets for small-to-mid size LWE instances with sparse binary secrets, and may scale to attack real-world LWE-based cryptosystems.

View on arXivView PDF

Code Implementations(1)

facebookresearch/SALSACommunity66%

Source code for the paper SALSA Attacking Lattice Cryptography with Transformers (Wenger et al., Neurips 2022)

298Python, Jupyter NotebookOct 31, 20223 years agoNOASSERTION

Similar Papers

Mage: Cracking Elliptic Curve Cryptography with Cross-Axis Transformers

87% match1 repo2025

SALSA PICANTE: a machine learning attack on LWE with binary secrets

86% match2023

A Provably Secure Strong PUF based on LWE: Construction and Implementation

85% match2023

Evaluating the Potential of Quantum Machine Learning in Cybersecurity: A Case-Study on PCA-based Intrusion Detection Systems

84% match1 repo32025

Towards quantum machine learning for assessing the resilience of post-quantum cryptography

84% match2026

Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic

84% match1 repo112024

Cite this paper

@article{wenger2022salsa,
  title  = {SALSA: Attacking Lattice Cryptography with Transformers},
  author = {Emily Wenger and Mingjie Chen and François Charton and Kristin Lauter},
  year   = {2022},
  eprint = {2207.04785},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.04785v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.04785.svg)](https://codeofpaper.com/paper/2207.04785)

Discussion