AI RESEARCH
Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks
arXiv CS.LG
•
ArXi:2604.16834v1 Announce Type: cross Privacy-preserving machine learning (PPML) has become increasingly important in applications where sensitive data must remain confidential. Homomorphic Encryption (HE) enables computation directly on encrypted data, allowing neural network inference without revealing raw inputs. While prior works have largely focused on inference over a single encrypted image, batch processing of encrypted inputs lags behind, despite being critical for high-throughput inference scenarios and.