一句话：提出 HEPIC，让客户端按需介入同态加密的密文管理，通过流水线重叠计算与通信，大幅加速私有推理且精度无损。
同态加密（HE）可在机器学习即服务中实现私有推理（PI），同时保护客户端输入与服务器端神经网络参数。现有 HE 方案多采用 fire-and-forget 模式，由服务器独自承担 bootstrapping、方案与参数转换等昂贵的密文管理，成为性能瓶颈；而 MPC 交互方案虽引入客户端参与，却带来通信开销。HEPIC 探索新的设计点：让客户端仅介入 HE 操作所需的密文管理。由于密文管理在客户端与服务器上语义一致，开发者可自行决定其执行位置与频率，从而在计算、通信与密文配置之间进行细粒度权衡。为实现这一执行模式，HEPIC 利用依赖感知流水线与流式传输重叠客户端重加密、服务器计算和通信，并引入缓存感知任务分配器（CATA）与成本感知客户端介入调度器（CACIS），以利用密文级并行并缓解客户端-服务器性能差异导致的停顿。评估表明，相比最先进的 fire-and-forget HE 私有推理系统，HEPIC 取得 2.20–41.93× 的加速，同时推理精度零损失。
Homomorphic Encryption (HE) enables Private Inference (PI) in Machine Learning as a Service (MLaaS), protecting both client inputs and server-side neural network (NN) parameters. Existing PI techniques are predominantly implemented as either HE-based fire-and-forget methods or MPC-based interactive methods. Recent HE-based PI systems improve the accuracy--performance trade-off via a layer-wise scheme and parameter switching, yet remain bottlenecked by fire-and-forget execution in which the server alone performs costly ciphertext management (e.g., bootstrapping and scheme/parameter conversions). We present HEPIC, an HE-based PI system that explores a different design point by leveraging client interventions for ciphertext managements. In a sense, HEPIC shares a common ground with MPC-based PI of being interactive with the client, but differs in that the client only intervenes for ciphertext managements required in HE operations. Because ciphertext management has identical semantics on the client and the server, HEPIC lets developers decide where and how often to execute it, enabling fine-grained trade-offs among computation, communication, and ciphertext configuration. HEPIC makes such execution practical by overlapping client re-encryption, server computation, and communication via dependency-aware pipelining and streaming-based transfers. We further enhance the performance with a cache-aware task allocator (CATA) and a cost-aware client intervention scheduler (CACIS) to exploit ciphertext-level parallelism and to mitigate stalls under client-server performance disparity. Our evaluation shows that HEPIC achieves up to 2.20--41.93× speedup over state-of-the-art fire-and-forget HE-based PI, while maintaining zero loss in inference accuracy.
@inproceedings{NamJHMP26,
title = {HEPIC: Private Inference over Homomorphic Encryption with Client Intervention},
author = {Kevin Nam and Youyeon Joo and Seungjin Ha and Hyungon Moon and Yunheung Paek},
booktitle = {ASPLOS},
year = {2026},
doi = {10.1145/3779212.3790170}
}