In collaborative machine learning, data valuation, i.e., evaluating the contribution of each client' data to the machine learning model, has become a critical task for incentivizing and selecting positive data contributions. However, existing studies often assume that clients engage in data valuation truthfully, overlooking the practical motivation for clients to exaggerate their contributions. To unlock this threat, this paper introduces the first data overvaluation attack, enabling strategic clients to have their data significantly overvalued. Furthermore, we propose a truthful data valuation metric, named Truth-Shapley. Truth-Shapley is the unique metric that guarantees some promising axioms for data valuation while ensuring that clients' optimal strategy is to perform truthful data valuation. Our experiments demonstrate the vulnerability of existing data valuation metrics to the data overvaluation attack and validate the robustness and effectiveness of Truth-Shapley.
View on arXiv@article{zheng2025_2502.00494,
title={ Data Overvaluation Attack and Truthful Data Valuation },
author={ Shuyuan Zheng and Sudong Cai and Chuan Xiao and Yang Cao and Jianbin Qin and Masatoshi Yoshikawa and Makoto Onizuka },
journal={arXiv preprint arXiv:2502.00494},
year={ 2025 }
}