Zero Knowledge Contingent Payments for Trained Neural Networks

Zhou, Zhelei; Cao, Xinle; Liu, Jian; Zhang, Bingsheng; Ren, Kui

doi:10.1007/978-3-030-88428-4_31

Cited by 4 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, even computing SV in plaintext could be expensive because it requires retraining models on different subsets of data; calculating them via MPC remains an open problem. As for the second dilemma, one natural idea is to leverage zeroknowledge contingent payment (ZKCP) [11], [12], [13], [14], which allows fair payment of digital goods and payments over a blockchain. However, simply applying ZKCP cannot ensure that data owners use the same data for both MPCbased data valuation and ZKCP.…”

Section: Introductionmentioning

confidence: 99%

Private Data Valuation and Fair Payment in Data Marketplaces

Tian¹,

Liu²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Data valuation is an essential task in a data marketplace. It aims at fairly compensating data owners for their contribution. There is increasing recognition in the machine learning community that the Shapley value-a foundational profit-sharing scheme in cooperative game theory-has major potential to value data, because it uniquely satisfies basic properties for fair credit allocation and has been shown to be able to identify data sources that are useful or harmful to model performance. However, calculating the Shapley value requires accessing original data sources. It still remains an open question how to design a realworld data marketplace that takes advantage of the Shapley value-based data pricing while protecting privacy and allowing fair payments.In this paper, we propose the first prototype of a data marketplace that values data sources based on the Shapley value in a privacy-preserving manner and at the same time ensures fair payments. Our approach is enabled by a suite of innovations on both algorithm and system design. We firstly propose a Shapley value calculation algorithm that can be efficiently implemented via multiparty computation (MPC) circuits. The key idea is to learn a performance predictor that can directly predict model performance corresponding to an input dataset without performing actual training. We further optimize the MPC circuit design based on the structure of the performance predictor. We further incorporate fair payment into the MPC circuit to guarantee that the data that the buyer pays for is exactly the same as the one that has been valuated. Our experimental results show that the proposed new data valuation algorithm is as effective as the original expensive one. Furthermore, the customized MPC protocol is efficient and scalable.

show abstract