SCOPE: Expanding Client-Side Post-Processing for Efficient Privacy-Preserving Model Inference
Shenchen Zhu, Kai Chen, Yue Zhao, Cheng'an Wei
2025Year
Abstract
Privacy-Preserving Inference (PPI) enables users to leverage powerful machine learning models without revealing sensitive input data. However, existing state-of-the-art solutions remain impractical due to significant computation and communication overheads.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get c54b951c-0386-486b-b49a-87ce82e847edRelated papers
- Enc2: Privacy-Preserving Inference for Tiny IoTs via Encoding and EncryptionHao-Jen Chien, Hossein Khalili, Amin Hass, Nader SehatbakhshMobiCom 2023 · 8 citations
- ABNN2: secure two-party arbitrary-bitwidth quantized neural network predictionsLiyan Shen, Ye Dong, Binxing Fang, Jinqiao Shi et al.DAC 2022 · 11 citations
- CryptoNAS: Private Inference on a ReLU BudgetZahra Ghodsi, Akshaj Kumar Veldanda, Brandon Reagen, Siddharth GargNeurIPS 2020 · 103 citations
- C2PI: An Efficient Crypto-Clear Two-Party Neural Network Private InferenceYuke Zhang, Dake Chen, Souvik Kundu, Haomei Liu et al.DAC 2023 · 7 citations
- PackCNN: Adaptive Data Packing for BSGS-Based Privacy-Preserving Convolutional Neural Network InferenceKanyu Ye, Haoping Yang, Honghui You, Yusi Chen et al.CCS 2026
