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: 13026
Venue: VLDB
Year: 2023
Pagerank: 6.8829966e-05
Overall Rank: 4,228 | 70.62%
DOI: 10.14778/3587136.3587141

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 9 of 9 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,082	Equitable Data Valuation Meets the Right to Be Forgotten in Model Markets	2023	VLDB	6.0457731e-05
8,548	Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation	2024	VLDB	5.4742553e-05
9,789	DP-starJ: A Differential Private Scheme towards Analytical Star-Join Queries	2023	SIGMOD	5.2719963e-05
10,107	Reliable and Private Utility Signaling for Data Markets	2026	SIGMOD	5.1725247e-05
10,403	Shapley Value Estimation Based on Differential Matrix	2025	SIGMOD	5.1725247e-05
10,694	PS-MI: Accurate, Efficient, and Private Data Valuation in Vertical Federated Learning	2025	VLDB	5.1725247e-05
10,723	Federated and Balanced Clustering for High-dimensional Data	2025	VLDB	5.1725247e-05
10,731	Privacy-Enhanced Database Synthesis for Benchmark Publishing	2025	VLDB	5.1725247e-05
10,981	A Profit-Maximizing Data Marketplace with Differentially Private Federated Learning under Price Competition	2024	SIGMOD	5.1725247e-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	0.00024695937
1,124	Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms	2019	VLDB	0.00012165727
3,724	Dealer: An End-to-End Model Marketplace with Differential Privacy	2021	VLDB	7.2364245e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
1,207	Privacy Preserving Vertical Federated Learning for Tree-based Models	2020	VLDB	0.00011770793
10,402	SecureXGB: A Secure and Efficient Multi-party Protocol for Vertical Federated XGBoost	2025	SIGMOD	5.1725247e-05
5,519	Federated Matrix Factorization with Privacy Guarantee	2022	VLDB	6.2518182e-05
11,240	Olive: Oblivious Federated Learning on Trusted Execution Environment Against the Risk of Sparsification	2023	VLDB	5.1725247e-05
11,212	FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning	2023	SIGMOD	5.1725247e-05
8,332	Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs	2024	VLDB	5.5057547e-05
4,410	Projected Federated Averaging with Heterogeneous Differential Privacy	2022	VLDB	6.7812717e-05
3,185	BlindFL: Vertical Federated Machine Learning without Peeking into Your Data	2022	SIGMOD	7.7267866e-05
11,046	Uldp-FL: Federated Learning with Across-Silo User-Level Differential Privacy	2024	VLDB	5.1725247e-05
8,548	Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation	2024	VLDB	5.4742553e-05