论文标题
Cryptonas：RELU预算的私人推论
CryptoNAS: Private Inference on a ReLU Budget
论文作者
论文摘要
机器学习作为一项服务已提高了围绕客户数据和提供商模型的隐私问题，并催化了私人推理（PI）研究：处理推断而不披露输入的方法。最近，研究人员已经改编了加密技术来表明PI是可能的，但是所有解决方案都会增加推理潜伏期超出实际限制。本文的观察是，现有模型不适合PI，并提出了一种名为Cryptonas的新型NAS方法，该方法是针对PI需求找到和量身定制模型的。关键见解是，在PI操作员中，延迟成本是非线性操作（例如，relu）主导延迟，而线性层有效自由。我们将Relu预算作为推理潜伏期的代理，并使用Cryptonas建立模型，以最大程度地提高给定预算的准确性。与最先进的情况相比，Cryptonas将准确性提高了3.4％，潜伏期提高了2.4倍。
Machine learning as a service has given raise to privacy concerns surrounding clients' data and providers' models and has catalyzed research in private inference (PI): methods to process inferences without disclosing inputs. Recently, researchers have adapted cryptographic techniques to show PI is possible, however all solutions increase inference latency beyond practical limits. This paper makes the observation that existing models are ill-suited for PI and proposes a novel NAS method, named CryptoNAS, for finding and tailoring models to the needs of PI. The key insight is that in PI operator latency cost are non-linear operations (e.g., ReLU) dominate latency, while linear layers become effectively free. We develop the idea of a ReLU budget as a proxy for inference latency and use CryptoNAS to build models that maximize accuracy within a given budget. CryptoNAS improves accuracy by 3.4% and latency by 2.4x over the state-of-the-art.
