arXiv 1801.032392018-01-10cs.CRcs.AI

Chameleon：一个面向机器学习应用的混合安全计算框架

Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications

UC San Diego（加州大学圣迭戈分校）；TU Darmstadt（达姆施塔特工业大学）

M. Sadegh Riazi, Christian Weinert, Oleksandr Tkachenko, Ebrahim M. Songhori, Thomas Schneider, Farinaz Koushanfar

摘要：

我们提出了变色龙，一种新的混合（混合协议）框架的安全功能评估（SFE），使双方能够共同计算的功能，而不透露他们的私人输入。Chameleon结合了通用SFE协议的最佳方面和基于附加秘密共享的协议。特别地，该框架使用加性秘密共享值在环$\mathbb{Z}_{2^l}$中执行线性操作，并且使用姚的乱码电路或Goldreich-Micali-Wigderson协议执行非线性操作。Chameleon偏离了加性或线性秘密共享模型的常见假设，其中三方或多方需要在在线阶段进行通信：该框架允许具有私人输入的两方在离线阶段在第三方节点生成相关随机性的假设下在在线阶段进行通信。几乎所有繁重的密码操作都是在离线阶段预先计算的，这大大减少了通信开销。Chameleon是可扩展的，并且比它所基于的ABY框架（NDSS'15）更有效。我们的框架支持带符号的定点数。特别地，Chameleon的有符号定点数的向量点积提高了基于大量矩阵乘法的算法的加密数据的挖掘和分类的效率。我们在5层卷积深度神经网络上对Chameleon的评估显示，执行速度分别比Microsoft CryptoNets（ICML'16）和MiniONN（CCS'17）快133倍和4.2倍。

英文摘要：

We present Chameleon, a novel hybrid (mixed-protocol) framework for secure function evaluation (SFE) which enables two parties to jointly compute a function without disclosing their private inputs. Chameleon combines the best aspects of generic SFE protocols with the ones that are based upon additive secret sharing. In particular, the framework performs linear operations in the ring $\mathbb{Z}_{2^l}$ using additively secret shared values and nonlinear operations using Yao's Garbled Circuits or the Goldreich-Micali-Wigderson protocol. Chameleon departs from the common assumption of additive or linear secret sharing models where three or more parties need to communicate in the online phase: the framework allows two parties with private inputs to communicate in the online phase under the assumption of a third node generating correlated randomness in an offline phase. Almost all of the heavy cryptographic operations are precomputed in an offline phase which substantially reduces the communication overhead. Chameleon is both scalable and significantly more efficient than the ABY framework (NDSS'15) it is based on. Our framework supports signed fixed-point numbers. In particular, Chameleon's vector dot product of signed fixed-point numbers improves the efficiency of mining and classification of encrypted data for algorithms based upon heavy matrix multiplications. Our evaluation of Chameleon on a 5 layer convolutional deep neural network shows 133x and 4.2x faster executions than Microsoft CryptoNets (ICML'16) and MiniONN (CCS'17), respectively.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文