[2604.03903] Improving ML Attacks on LWE with Data Repetition and Stepwise Regression

Computer Science > Cryptography and Security arXiv:2604.03903 (cs) [Submitted on 5 Apr 2026] Title:Improving ML Attacks on LWE with Data Repetition and Stepwise Regression Authors:Alberto Alfarano, Eshika Saxena, Emily Wenger, François Charton, Kristin Lauter View a PDF of the paper titled Improving ML Attacks on LWE with Data Repetition and Stepwise Regression, by Alberto Alfarano and 4 other authors View PDF HTML (experimental) Abstract: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. Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2604.03903 [cs.CR]   (or arXiv:2604.03903v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.03903 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission hist...