mlsanityData to 7 Oct 2026

OLIVE: Oblivious Federated Learning on Trusted Execution Environment against the risk of sparsification

arXiv 2202.07165 ↗First posted 15 Feb 2022cs.LG cs.CRcited by 4

Not on the map. Why?

Abstract (arXiv)

Combining Federated Learning (FL) with a Trusted Execution Environment (TEE) is a promising approach for realizing privacy-preserving FL, which has garnered significant academic attention in recent years. Implementing the TEE on the server side enables each round of FL to proceed without exposing the client's gradient information to untrusted servers. This addresses usability gaps in existing secure aggregation schemes as well as utility gaps in differentially private FL. However, to address the issue using a TEE, the vulnerabilities of server-side TEEs need to be considered -- this has not been sufficiently investigated in the context of FL. The main technical contribution of this study is the analysis of the vulnerabilities of TEE in FL and the defense. First, we theoretically analyze the leakage of memory access patterns, revealing the risk of sparsified gradients, which are commonly used in FL to enhance communication efficiency and model accuracy. Second, we devise an inference attack to link memory access patterns to sensitive information in the training dataset. Finally, we propose an oblivious yet efficient aggregation algorithm to prevent memory access pattern leakage. Our experiments on real-world data demonstrate that the proposed method functions efficiently in practical scales.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 98 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

45 of 98 references.

References · 45

  1. 2016Deep Learning with Differential Privacycited by 2,682
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2018How To Backdoor Federated Learningcited by 745
  6. 2017Renyi Differential Privacycited by 643
  7. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  8. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 471
  9. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  10. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  11. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  12. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
33 more
  1. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  2. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 234
  3. 2019Differentially Private Learning with Adaptive Clippingcited by 218
  4. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
  5. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 163
  6. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  7. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  8. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  9. 2019Federated Learning for Emoji Prediction in a Mobile Keyboardcited by 115
  10. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  11. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 84
  12. 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 74
  13. 2019The Privacy Blanket of the Shuffle Modelcited by 73
  14. 2020LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacycited by 63
  15. 2021Rethinking gradient sparsification as total error minimizationcited by 41
  16. 2021Communication Efficiency in Federated Learning: Achievements and Challengescited by 40
  17. 2020Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluationcited by 39
  18. 2018Chiron: Privacy-preserving Machine Learning as a Servicecited by 38
  19. 2020FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selectioncited by 35
  20. 2019Efficient Privacy-Preserving Stochastic Nonconvex Optimizationcited by 27
  21. 2020FLAME: Differentially Private Federated Learning in the Shuffle Modelcited by 27
  22. 2020A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysiscited by 26
  23. 2021User-Level Label Leakage from Gradients in Federated Learningcited by 21
  24. 2017Software Grand Exposure: SGX Cache Attacks Are Practicalcited by 14
  25. 2021Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGXcited by 14
  26. 2018SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Executioncited by 13
  27. 2016Inferring Fine-grained Control Flow Inside SGX Enclaves with Branch Shadowingcited by 10
  28. 2020A Survey of Published Attacks on Intel SGXcited by 10
  29. 2021Separation of Powers in Federated Learningcited by 8
  30. 2021Sparsified Secure Aggregation for Privacy-Preserving Federated Learningcited by 8
  31. 2018An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processorscited by 5
  32. 2020PCT-TEE: Trajectory-based Private Contact Tracing System with Trusted Execution Environmentcited by 2
  33. 2021The Privacy-preserving Padding Problem: Non-negative Mechanisms for Conservative Answers with Differential Privacycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 1; 2026: 1.

4 papers.

  1. 2023FedBone: Towards Large-Scale Federated Multi-Task Learningcited by 14
  2. 2023ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacycited by 9
  3. 2025On the Inference (In-)Security of Vertical Federated Learning: Efficient Auditing against Inference Tampering Attackcited by 0
  4. 2026QoS-Aware Token Scheduling and Private Data Valuation for Multi-Modal Agentic Networkscited by 0