AI RESEARCH
Improving ML Attacks on LWE with Data Repetition and Stepwise Regression
arXiv CS.LG
•
ArXi:2604.03903v1 Announce Type: cross 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 nstrated 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, 2024) on samples pre-processed with BKZ. We show that using larger.