Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption

Moran Baruch,Nir Drucker, Gilad Ezov, Eyal Kushnir, Jenny Lerner, Omri Soceanu, Itamar Zimerman

arXiv (Cornell University)(2023)

引用 0|浏览0
暂无评分
摘要
Training large-scale CNNs that during inference can be run under Homomorphic Encryption (HE) is challenging due to the need to use only polynomial operations. This limits HE-based solutions adoption. We address this challenge and pioneer in providing a novel training method for large polynomial CNNs such as ResNet-152 and ConvNeXt models, and achieve promising accuracy on encrypted samples on large-scale dataset such as ImageNet. Additionally, we provide optimization insights regarding activation functions and skip-connection latency impacts, enhancing HE-based evaluation efficiency. Finally, to demonstrate the robustness of our method, we provide a polynomial adaptation of the CLIP model for secure zero-shot prediction, unlocking unprecedented capabilities at the intersection of HE and transfer learning.
更多
查看译文
关键词
large scale polynomial cnns,e2e inference
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要