面向同态加密下端到端推理的大规模多项式CNN训练
Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption
- IBM Research（IBM研究院）
- Bar-Ilan University（巴伊兰大学）
- AI2（艾伦人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出新型训练方法，实现可在同态加密下运行的大规模多项式CNN训练，在ImageNet上取得可观精度，还优化了HE评估效率，并通过多项式适配CLIP实现安全零样本预测。
AI中文摘要：
训练推理阶段可在同态加密（HE）下运行的大规模CNN颇具挑战，因为仅能使用多项式运算，这限制了基于HE的方案的应用。我们应对了这一挑战，率先提出针对ResNet-152、ConvNeXt等大型多项式CNN的新型训练方法，在ImageNet等大规模数据集的加密样本上取得了可观的精度。此外，我们还给出了激活函数与跳跃连接延迟影响的优化洞见，提升了基于HE的评估效率。最后，为验证方法的鲁棒性，我们对CLIP模型进行多项式适配以实现安全零样本预测，解锁了HE与迁移学习交叉领域前所未有的能力。
英文摘要：
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.
