TransNet: Training Privacy-Preserving Neural Network over Transformed Layer

Summary: TransNet proposes a privacy-preserving collaborative neural network using a transformed layer to support arbitrarily partitioned data, with a server that pools transformed data. It reduces computation and communication compared with MPC/HE, requires no special security on the training server, and achieves near-baseline accuracy across varying participant counts. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: h6c672703d2239dfc
Venue: VLDB
Year: 2020
Pagerank: 5.1038322e-05
Overall Rank: 9,968 | 32.99%
DOI: 10.14778/3407790.3407794

Incoming Non-self Citations Over Time

Authors

1. Qijian He (University of Science and Technology Beijing)
2. Wei Yang (University of Science and Technology Beijing)
3. Bingren Chen (University of Science and Technology Beijing)
4. Yangyang Geng (University of Science and Technology Beijing)
5. Liusheng Huang (University of Science and Technology Beijing)

BibTeX Citation

@article{he_vldb20,
        title = {{TransNet: Training Privacy-Preserving Neural Network over Transformed Layer}},
        author = {He, Qijian and Yang, Wei and Chen, Bingren and Geng, Yangyang and Huang, Liusheng},
        journal = {PVLDB},
        series = {{VLDB} '20},
        volume = {13},
        number = {11},
        pages = {1849--1862},
        doi = {10.14778/3407790.3407794},
        url = {https://doi.org/10.14778/3407790.3407794},
        year = {2020}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,587	Privacy-preserving and Verifiable Causal Prescriptive Analytics	2026	SIGMOD	4.9793485e-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
68	Privacy-Preserving Data Mining	2000	SIGMOD	0.00037958605
2,307	Secure kNN Computation on Encrypted Databases	2009	SIGMOD	8.6665657e-05
5,285	Functional Mechanism: Regression Analysis under Differential Privacy	2012	VLDB	6.1975714e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,751	Olive: Oblivious Federated Learning on Trusted Execution Environment Against the Risk of Sparsification	2023	VLDB
2	2,165	Data Synthesis based on Generative Adversarial Networks	2018	VLDB
3	3,684	Secure Shapley Value for Cross-Silo Federated Learning	2023	VLDB
4	3,293	Privacy-preserving Anonymization of Set-valued Data	2008	VLDB
5	3,311	BlindFL: Vertical Federated Machine Learning without Peeking into Your Data	2022	SIGMOD
6	4,541	Projected Federated Averaging with Heterogeneous Differential Privacy	2022	VLDB
7	6,335	A Neural Approach to Spatio-Temporal Data Release with User-Level Differential Privacy	2023	SIGMOD
8	1,277	Privacy Preserving Vertical Federated Learning for Tree-based Models	2020	VLDB
9	10,341	Distributed Learning of Fully Connected Neural Networks using Independent Subnet Training	2022	VLDB
10	6,539	Skellam Mixture Mechanism: a Novel Approach to Federated Learning with Differential Privacy	2022	VLDB