Secure Shapley Value for Cross-Silo Federated Learning

Summary: Secure Shapley-value computation for cross-silo FL without exposing client models or test data; proposes HESV (one-server HE) and SecSV (two-server) for privacy-preserving contribution evaluation. SecSV uses a hybrid HE/plaintext scheme, efficient secure matrix multiplication, and selective test-sample skipping to avoid expensive ciphertext–ciphertext multiplications, achieving 7.2–36.6× speedups over HESV with minor SV accuracy loss. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 13213
Venue: VLDB
Year: 2023
Pagerank: 6.8980966e-05
Overall Rank: 4,106 | 71.84%
DOI: 10.14778/3587136.3587141

Incoming Non-self Citations Over Time

Authors

1. Shuyuan Zheng (Kyoto University)
2. Yang Cao (Hokkaido University)
3. Masatoshi Yoshikawa (Kyoto University)

BibTeX Citation

@article{zheng_vldb23,
        title = {{Secure Shapley Value for Cross-Silo Federated Learning}},
        author = {Zheng, Shuyuan and Cao, Yang and Yoshikawa, Masatoshi},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {7},
        pages = {1657--1670},
        doi = {10.14778/3587136.3587141},
        url = {https://doi.org/10.14778/3587136.3587141},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 10 of 10 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,145	Equitable Data Valuation Meets the Right to Be Forgotten in Model Markets	2023	VLDB	5.9604471e-05
8,045	Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation	2024	VLDB	5.5008615e-05
9,171	DP-starJ: A Differential Private Scheme towards Analytical Star-Join Queries	2023	SIGMOD	5.3093185e-05
9,541	Shapley Value Estimation Based on Differential Matrix	2025	SIGMOD	5.2528121e-05
10,198	ASSS: Adaptive Stratified Sampling for Shapley-like Values	2026	SIGMOD	5.093636e-05
10,397	Reliable and Private Utility Signaling for Data Markets	2026	SIGMOD	5.093636e-05
10,934	PS-MI: Accurate, Efficient, and Private Data Valuation in Vertical Federated Learning	2025	VLDB	5.093636e-05
10,959	Federated and Balanced Clustering for High-dimensional Data	2025	VLDB	5.093636e-05
10,967	Privacy-Enhanced Database Synthesis for Benchmark Publishing	2025	VLDB	5.093636e-05
11,191	A Profit-Maximizing Data Marketplace with Differentially Private Federated Learning under Price Competition	2024	SIGMOD	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 3 of 3 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
218	Limiting Privacy Breaches in Privacy Preserving Data Mining	2003	PODS	0.00024420564
1,066	Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms	2019	VLDB	0.00012333161
3,759	Dealer: An End-to-End Model Marketplace with Differential Privacy	2021	VLDB	7.14674e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	1,249	Privacy Preserving Vertical Federated Learning for Tree-based Models	2020	VLDB
2	10,678	SecureXGB: A Secure and Efficient Multi-party Protocol for Vertical Federated XGBoost	2025	SIGMOD
3	5,588	Federated Matrix Factorization with Privacy Guarantee	2022	VLDB
4	11,438	Olive: Oblivious Federated Learning on Trusted Execution Environment Against the Risk of Sparsification	2023	VLDB
5	11,411	FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning	2023	SIGMOD
6	8,456	Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs	2024	VLDB
7	4,446	Projected Federated Averaging with Heterogeneous Differential Privacy	2022	VLDB
8	3,237	BlindFL: Vertical Federated Machine Learning without Peeking into Your Data	2022	SIGMOD
9	11,252	Uldp-FL: Federated Learning with Across-Silo User-Level Differential Privacy	2024	VLDB
10	8,045	Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation	2024	VLDB