mlsanityData to 7 Oct 2026

A Survey of Secure Computation Using Trusted Execution Environments

arXiv 2302.12150 ↗First posted 23 Feb 2023cs.CR cs.AI cs.DBcited by 8

Not on the map. Why?

Abstract (arXiv)

As an essential technology underpinning trusted computing, the trusted execution environment (TEE) allows one to launch computation tasks on both on- and off-premises data while assuring confidentiality and integrity. This article provides a systematic review and comparison of TEE-based secure computation protocols. We first propose a taxonomy that classifies secure computation protocols into three major categories, namely secure outsourced computation, secure distributed computation and secure multi-party computation. To enable a fair comparison of these protocols, we also present comprehensive assessment criteria with respect to four aspects: setting, methodology, security and performance. Based on these criteria, we review, discuss and compare the state-of-the-art TEE-based secure computation protocols for both general-purpose computation functions and special-purpose ones, such as privacy-preserving machine learning and encrypted database queries. To the best of our knowledge, this article is the first survey to review TEE-based secure computation protocols and the comprehensive comparison can serve as a guideline for selecting suitable protocols for deployment in practice. Finally, we also discuss several future research directions and challenges.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 165 references that are in the map. First posted on arXiv 23 Feb 2023.

Builds on

31 of 165 references.

References · 31

  1. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 101
  2. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  3. 2020FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learningcited by 74
  4. 2019CrypTFlow: Secure TensorFlow Inferencecited by 61
  5. 2020DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environmentscited by 57
  6. 2018Chiron: Privacy-preserving Machine Learning as a Servicecited by 38
  7. 2018MLCapsule: Guarded Offline Deployment of Machine Learning as a Servicecited by 29
  8. 2019Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environmentscited by 17
  9. 2021Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGXcited by 14
  10. 2022DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardwarecited by 13
  11. 2021secureTF: A Secure TensorFlow Frameworkcited by 12
  12. 20213LegRace: Privacy-Preserving DNN Training over TEEs and GPUscited by 9
19 more
  1. 2019TensorSCONE: A Secure TensorFlow Framework using Intel SGXcited by 8
  2. 2020A Survey of Coded Distributed Computingcited by 8
  3. 2019Conclave: secure multi-party computation on big data (extended TR)cited by 7
  4. 2019A Hybrid Approach to Secure Function Evaluation Using SGXcited by 6
  5. 2016SMCQL: Secure Querying for Federated Databasescited by 5
  6. 2018An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processorscited by 5
  7. 2018Confidential Inference via Ternary Model Partitioningcited by 5
  8. 2018Shrinkwrap: Differentially-Private Query Processing in Private Data Federationscited by 5
  9. 2021Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspectivecited by 4
  10. 2017HardIDX: Practical and Secure Index with SGXcited by 2
  11. 2017StealthDB: a Scalable Encrypted Database with Full SQL Query Supportcited by 2
  12. 2020Oblivious Sampling Algorithms for Private Data Analysiscited by 2
  13. 2020PCT-TEE: Trajectory-based Private Contact Tracing System with Trusted Execution Environmentcited by 2
  14. 2021Plinius: Secure and Persistent Machine Learning Model Trainingcited by 2
  15. 2016The Circle Game: Scalable Private Membership Test Using Trusted Hardwarecited by 1
  16. 2016The bumpy road towards iPhone 5c NAND mirroringcited by 1
  17. 2017LightBox: Full-stack Protected Stateful Middlebox at Lightning Speedcited by 1
  18. 2020Efficient Oblivious Database Joinscited by 1
  19. 2021On Optimizing the Trade-off between Privacy and Utility in Data Provenancecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 2.

8 papers.

  1. 2025Is Your LLM Overcharging You? Tokenization, Transparency, and Incentivescited by 13
  2. 2025Spore in the Wild: A Case Study of Spore.fun as an Open-Environment Evolution Experiment with Sovereign AI Agents on TEE-Secured Blockchainscited by 5
  3. 2024Tempo: Confidentiality Preservation in Cloud-Based Neural Network Trainingcited by 2
  4. 2024Privacy-Preserving and Trustworthy Deep Learning for Medical Imagingcited by 0
  5. 2025Provably Secure Retrieval-Augmented Generationcited by 0
  6. 2025PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networkscited by 0
  7. 2026Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Modelscited by 0
  8. 2026RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Controlcited by 0