Olive: Oblivious Federated Learning on Trusted Execution Environment Against the Risk of Sparsification
Summary: Exposes a previously overlooked TEE vulnerability in federated learning: sparsified gradients leak sensitive training information through memory-access patterns exploitable by inference attacks. Introduces an efficient oblivious aggregation algorithm that masks these patterns at practical scale. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Fumiyuki Kato (Kyoto University)
- 2. Yang Cao (Hokkaido University)
- 3. Masatoshi Yoshikawa (Osaka Seikei University)
BibTeX Citation
@article{kato_vldb23,
title = {{Olive: Oblivious Federated Learning on Trusted Execution Environment Against the Risk of Sparsification}},
author = {Kato, Fumiyuki and Cao, Yang and Yoshikawa, Masatoshi},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {10},
pages = {2404--2417},
doi = {10.14778/3603581.3603583},
url = {https://doi.org/10.14778/3603581.3603583},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,252 | Uldp-FL: Federated Learning with Across-Silo User-Level Differential Privacy | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,859 | Adore: Differentially Oblivious Relational Database Operators | 2023 | VLDB | 7.0670506e-05 |
| 6,601 | What Is the Price for Joining Securely? Benchmarking Equi-Joins in Trusted Execution Environments | 2022 | VLDB | 5.8246671e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 13,355 | Communication Efficient and Provable Federated Unlearning | 2024 | VLDB |
| 2 | 8,045 | Contributions Estimation in Federated Learning: A Comprehensive Experimental Evaluation | 2024 | VLDB |
| 3 | 8,456 | Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs | 2024 | VLDB |
| 4 | 5,645 | OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitization | 2023 | VLDB |
| 5 | 4,106 | Secure Shapley Value for Cross-Silo Federated Learning | 2023 | VLDB |
| 6 | 5,588 | Federated Matrix Factorization with Privacy Guarantee | 2022 | VLDB |
| 7 | 6,366 | Practical Differentially Private and Byzantine-resilient Federated Learning | 2023 | SIGMOD |
| 8 | 4,446 | Projected Federated Averaging with Heterogeneous Differential Privacy | 2022 | VLDB |
| 9 | 1,249 | Privacy Preserving Vertical Federated Learning for Tree-based Models | 2020 | VLDB |
| 10 | 3,237 | BlindFL: Vertical Federated Machine Learning without Peeking into Your Data | 2022 | SIGMOD |