AI RESEARCH
CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption
arXiv CS.LG
•
ArXi:2602.01621v3 Announce Type: replace-cross Homomorphic encryption (HE) is a prominent framework for privacy-preserving machine learning, enabling inference directly on encrypted data. However, evaluating softmax, a core component of transformer architectures, remains particularly challenging in HE due to its multivariate structure, the large dynamic range induced by exponential functions, and the costly division operation. In this paper, we propose CGF-softmax, which reformulates the softmax denominator through the cumulant generating function