对比加密与电路混淆在隐私计算中的表现，揭示各自优劣。
Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference
- 用CKKS方案和TinyGarble2.0实现两层神经网络推理
- 电路混淆更快、内存更低，但需多轮通信；加密可非交互
- 适合关注效率或通信成本的研究者与工程师
机器学习正广泛应用于医疗、金融和自然语言处理等领域，数据隐私与模型机密性问题日益突出。隐私保护机器学习（PPML）通过密码学安全计算技术，实现在不泄露敏感输入或专有模型的前提下进行推理。本文对比了两种主流方法：全同态加密（FHE）与电路混淆（GC）。采用微软SEAL库的CKKS方案（FHE）与IntelLabs的TinyGarble2.0框架（GC），在半诚实威胁模型下对两层神经网络进行评估，指标包括推理输出误差、往返时间、峰值内存使用、通信开销和通信轮数。结果表明：电路混淆在执行速度和内存消耗上更优，但需多轮通信；而全同态加密支持非交互式推理，适合对通信轮数敏感的场景。
原文摘要 · Abstract (English)
Machine Learning (ML) is making its way into fields such as healthcare, finance, and Natural Language Processing (NLP), and concerns over data privacy and model confidentiality continue to grow. Privacy-preserving Machine Learning (PPML) addresses this challenge by enabling inference on private data without revealing sensitive inputs or proprietary models. Leveraging Secure Computation techniques from Cryptography, two widely studied approaches in this domain are Fully Homomorphic Encryption (FHE) and Garbled Circuits (GC). This work presents a comparative evaluation of FHE and GC for secure neural network inference. A two-layer neural network (NN) was implemented using the CKKS scheme from the Microsoft SEAL library (FHE) and the TinyGarble2.0 framework (GC) by IntelLabs. Both implementations are evaluated under the semi-honest threat model, measuring inference output error, round-trip time, peak memory usage, communication overhead, and communication rounds. Results reveal a trade-off: modular GC offers faster execution and lower memory consumption, while FHE supports non-interactive inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。