a machine learning attack on Learning With Errors with sparse small secrets Cathy Y uanchen Li FAIR, Meta Emily Wenger The University of Chicago Zeyuan Allen-Zhu FAIR, Meta Francois Charton

Feb-16-2026, 09:04:08 GMT–Neural Information Processing Systems 

For example, HE uses secrets with small entries, and the HE community has considered standardizing small sparse secrets to improve efficiency and functionality.