← Search

Moran Baruch

2 accepted papers

2024

Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption

ICML 2024poster

Designing privacy-preserving DL solutions is a major challenge within the AI community. Homomorphic Encryption (HE) has emerged as one of the most promising approaches in this realm, enabling the decoupling of knowledge between a model owner and a data owner. Despite extensive research and applicati…

Cited by 24SourcePDFScholar
2019

A Little Is Enough: Circumventing Defenses For Distributed Learning

NeurIPS 2019poster

Distributed learning is central for large-scale training of deep-learning models. However, it is exposed to a security threat in which Byzantine participants can interrupt or control the learning process. Previous attack models assume that the rogue participants (a) are omniscient (know the data of…