SALSA: Attacking Lattice Cryptography with Transformers

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 mix half-trained models and 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.

PDF NeurIPS OpenReview Semantic Scholar

Cite

Text

Wenger et al. "SALSA: Attacking Lattice Cryptography with Transformers." Neural Information Processing Systems, 2022.

Markdown

[Wenger et al. "SALSA: Attacking Lattice Cryptography with Transformers." Neural Information Processing Systems, 2022.](https://mlanthology.org/neurips/2022/wenger2022neurips-salsa/)

BibTeX

@inproceedings{wenger2022neurips-salsa,
  title     = {{SALSA: Attacking Lattice Cryptography with Transformers}},
  author    = {Wenger, Emily and Chen, Mingjie and Charton, Francois and Lauter, Kristin E.},
  booktitle = {Neural Information Processing Systems},
  year      = {2022},
  url       = {https://mlanthology.org/neurips/2022/wenger2022neurips-salsa/}
}