Improving ML Attacks on LWE with Data Repetition and Stepwise Regression
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915916440141824 |
|---|---|
| author | Alfarano, Alberto Saxena, Eshika Wenger, Emily Charton, François Lauter, Kristin |
| author_facet | Alfarano, Alberto Saxena, Eshika Wenger, Emily Charton, François Lauter, Kristin |
| contents | The Learning with Errors (LWE) problem is a hard math problem in lattice-based cryptography. In the simplest case of binary secrets, it is the subset sum problem, with error. Effective ML attacks on LWE were demonstrated in the case of binary, ternary, and small secrets, succeeding on fairly sparse secrets. The ML attacks recover secrets with up to 3 active bits in the "cruel region" (Nolte et al., 2024) on samples pre-processed with BKZ. We show that using larger training sets and repeated examples enables recovery of denser secrets. Empirically, we observe a power-law relationship between model-based attempts to recover the secrets, dataset size, and repeated examples. We introduce a stepwise regression technique to recover the "cool bits" of the secret. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03903 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Improving ML Attacks on LWE with Data Repetition and Stepwise Regression Alfarano, Alberto Saxena, Eshika Wenger, Emily Charton, François Lauter, Kristin Cryptography and Security Machine Learning The Learning with Errors (LWE) problem is a hard math problem in lattice-based cryptography. In the simplest case of binary secrets, it is the subset sum problem, with error. Effective ML attacks on LWE were demonstrated in the case of binary, ternary, and small secrets, succeeding on fairly sparse secrets. The ML attacks recover secrets with up to 3 active bits in the "cruel region" (Nolte et al., 2024) on samples pre-processed with BKZ. We show that using larger training sets and repeated examples enables recovery of denser secrets. Empirically, we observe a power-law relationship between model-based attempts to recover the secrets, dataset size, and repeated examples. We introduce a stepwise regression technique to recover the "cool bits" of the secret. |
| title | Improving ML Attacks on LWE with Data Repetition and Stepwise Regression |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2604.03903 |