Olive: Oblivious Federated Learning on Trusted Execution Environment Against the Risk of Sparsification
Summary: Analyzes server-side TEE memory-access leakage in federated learning, showing sparsified gradients expose sensitive training data via access patterns. Proposes an efficient oblivious aggregation algorithm that prevents access-pattern leakage while remaining practical at scale. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Fumiyuki Kato
- 2. Yang Cao
- 3. Masatoshi Yoshikawa
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,043 | Uldp-FL: Federated Learning with Across-Silo User-Level Differential Privacy | 2024 | VLDB | 4.1945683e-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 |
|---|---|---|---|---|
| 4,036 | Adore: Differentially Oblivious Relational Database Operators | 2023 | VLDB | 6.5089579e-05 |
| 5,784 | What Is the Price for Joining Securely? Benchmarking Equi-Joins in Trusted Execution Environments | 2022 | VLDB | 5.328804e-05 |
Previous
Page 1 / 1
Next