论文标题
CryptFlow2：实用的2方安全推理
CrypTFlow2: Practical 2-Party Secure Inference
论文作者
论文摘要
我们提出了Cryptflow2，这是一种使用安全的2派对计算，用于对现实的深神经网络（DNN）进行安全推断的加密框架。 cryptflow2协议都是正确的 - 即它们的输出等同于clearText的执行 - 且高效 - 它们在延迟和规模上都优于最新协议。在Cryptflow2的核心中，我们有了新的2PC协议，可用于安全比较和除法，旨在平衡圆形和通信复杂性，以实现安全推理任务。使用cryptflow2，我们提出了对Imagenet尺度DNN（例如Resnet50和densenet121）的第一个安全推断。这些DNN至少比在2派对DNN推断的工作中所考虑的数量级要大。即使在先前工作考虑的基准上，Cryptflow2也需要比最先进的时间少的数量级和20x-30x的时间。
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both correct -- i.e., their outputs are bitwise equivalent to the cleartext execution -- and efficient -- they outperform the state-of-the-art protocols in both latency and scale. At the core of CrypTFlow2, we have new 2PC protocols for secure comparison and division, designed carefully to balance round and communication complexity for secure inference tasks. Using CrypTFlow2, we present the first secure inference over ImageNet-scale DNNs like ResNet50 and DenseNet121. These DNNs are at least an order of magnitude larger than those considered in the prior work of 2-party DNN inference. Even on the benchmarks considered by prior work, CrypTFlow2 requires an order of magnitude less communication and 20x-30x less time than the state-of-the-art.
