arXiv · 2611.15373
SecDVA: A Maliciously Secure Multi-Party Framework for Data Value Assessment in Modern Machine Learning Data Markets
Abstract
Data Value Assessment (DVA) plays a critical role in modern data markets by enabling buyers to evaluate how a seller's data would improve model performance before purchase. However, existing DVA approaches require one party to reveal the data or model, exposing participants to privacy leakage, strategic manipulation, and high deployment costs. These limitations motivate a DVA protocol that is secure, reliable, widely applicable, and efficient enough for practical deployment in modern data markets. In this paper, we present SecDVA, the first maliciously secure multi-party computation (MPC) framework for reliable and practical DVA in modern machine learning data markets. SecDVA ensures that neither the seller's data nor the buyer's model and test data are disclosed beyond the final DVA outcome, while remaining robust against malicious behavior. To address the efficiency and applicability challenges of DVA for large models, we use the neural tangent kernel theory to linearize model updates and introduce lightweight mini-batch approximations to significantly reduce computation overhead. We further design a (2+1)-party MPC protocol based on function secret sharing, together with optimized non-linear primitives. In addition, we optimize the underlying MPC backends, the distributed point function, and the distributed comparison function, reducing the number of Advanced Encryption Standard calls to improve efficiency. Extensive experiments demonstrate that SecDVA outperforms existing baselines in the plaintext setting and enables DVA for large-scale models in a reasonable time under MPC.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Lixu Wang, Xinpeng Yang, Meng Hao, Guangyi Zhang, Tianwei Zhang, Wei Dong, Chenkai Weng. 2026-11-11. SecDVA: A Maliciously Secure Multi-Party Framework for Data Value Assessment in Modern Machine Learning Data Markets. https://searcharxiv.com/abs/2611.15373
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.