Paper 2021/673
zkCNN: Zero Knowledge Proofs for Convolutional Neural Network Predictions and Accuracy
Tianyi Liu and Xiang Xie and Yupeng Zhang
Abstract
Deep learning techniques with neural networks are developing prominently in recent years and have been deployed in numerous applications. Despite their great success, in many scenarios it is important for the users to validate that the inferences are truly computed by legitimate neural networks with high accuracy, which is referred as the integrity of machine learning predictions. To address this issue, in this paper, we propose zkCNN, a zero knowledge proof scheme for convolutional neural networks (CNN). The scheme allows the owner of the CNN model to prove to others that the prediction of a data sample is indeed calculated by the model, without leaking any information about the model itself. Our scheme can also be generalized to prove the accuracy of a secret CNN model on public dataset. Underlying zkCNN is a new sumcheck protocol for proving fast Fourier transforms and convolutions with a linear prover time, which is even faster than computing the result asymptotically. We also introduce several improvements and generalizations on the interactive proofs for CNN predictions, including verifying the convolutional layers, the activation function of ReLU and the max pooling. Our scheme is highly efficient in practice. It can scale to the large CNN of VGG16 with 15 million parameters and 16 layers. It only takes 163 seconds to generate the proof, which is 1000x faster than existing schemes. The proof size is 230 kilobytes, and the verifier time is only 172 milliseconds. Our scheme can further scale to prove the accuracy of the same CNN on 100 images.
Metadata
- Available format(s)
- Category
- Cryptographic protocols
- Publication info
- Preprint. MINOR revision.
- Keywords
- Zero knowledge proofsMachine learningConvolutional Neural Networks
- Contact author(s)
- zhangyp @ tamu edu,xiexiang @ matrixelements com,tianyi @ tamu edu
- History
- 2023-02-18: last of 2 revisions
- 2021-05-25: received
- See all versions
- Short URL
- https://ia.cr/2021/673
- License
-
CC BY