As ML models have increased in capabilities and accuracy, so has the complexity of their deployments. Increasingly, ML model consumers are turning to service providers to serve the ML models in the ML-as-a-service (MLaaS) paradigm. As MLaaS proliferates, a critical requirement emerges: how can model consumers verify that the correct predictions were served, in the face of malicious, lazy, or buggy service providers? In this work, we present the first practical ImageNet-scale method to verify ML model inference non-interactively, i.e., after the inference has been done. To do so, we leverage recent developments in ZK-SNARKs (zero-knowledge succinct non-interactive argument of knowledge), a form of zero-knowledge proofs. ZK-SNARKs allows us to verify ML model execution non-interactively and with only standard cryptographic hardness assumptions. In particular, we provide the first ZK-SNARK proof of valid inference for a full resolution ImageNet model, achieving 79\% top-5 accuracy. We further use these ZK-SNARKs to design protocols to verify ML model execution in a variety of scenarios, including for verifying MLaaS predictions, verifying MLaaS model accuracy, and using ML models for trustless retrieval. Together, our results show that ZK-SNARKs have the promise to make verified ML model inference practical.
翻译:随着ML模型的容量和准确性提高,其部署的复杂程度也随之提高。ML模型消费者越来越多地转向服务供应商,为ML-as-service(MLAAS)模式中的ML模型服务。随着MLAAS的激增,一项关键要求出现:在恶意、懒惰或错误服务供应商面前,消费者如何模型核实正确预测是否得到正确预测?在这项工作中,我们提出了第一个实际的图像网络尺度方法,用以核实ML模型的不互动性推论,即,在推断完成后,ML模型的不互动性推论。为了做到这一点,我们利用ZK-SNARK(零知识简明非互动的简单非互动的知识论证)系统的最新发展,一种零知识证明的形式。ZK-SNARK(S)系统使我们能够核实MK模型的正确性执行,在MKS-SA(MK-K)系统(MKS)执行中,我们进一步使用MS-S-L(MNAR)系统(MS-L)系统(MS)的高级预测模型,在MS-S-L)的模拟设计中,我们用这些模型来核查MS-L(MS-S-L)程序来进一步使用这些模型的核查。