mlsanityData to 7 Oct 2026

DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments

arXiv 2004.05703 ↗First posted 12 Apr 2020cs.LG cs.CR stat.MLcited by 57

Not on the map. Why?

Abstract (arXiv)

We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices) are equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy risks as models can leak information about their training data through effective membership inference attacks (MIAs). We evaluate the performance of DarkneTZ, including CPU execution time, memory usage, and accurate power consumption, using two small and six large image classification models. Due to the limited memory of the edge device's TEE, we partition model layers into more sensitive layers (to be executed inside the device TEE), and a set of layers to be executed in the untrusted part of the operating system. Our results show that even if a single layer is hidden, we can provide reliable model privacy and defend against state of the art MIAs, with only 3% performance overhead. When fully utilizing the TEE, DarkneTZ provides model protections with up to 10% overhead.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 12; 2023: 13; 2024: 11; 2025: 3; 2026: 9.

57 papers.

Sort:

By area:

  1. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  2. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  3. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  4. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  5. 2023No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device MLcited by 21
  6. 2021It's always personal: Using Early Exits for Efficient On-Device CNN Personalisationcited by 18
  7. 2021Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputscited by 18
  8. 2021DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Devicecited by 17
  9. 2021Stealthy Backdoors as Compression Artifactscited by 17
  10. 2023FedBone: Towards Large-Scale Federated Multi-Task Learningcited by 14
  11. 2022DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardwarecited by 13
  12. 2022Machine Learning with Confidential Computing: A Systematization of Knowledgecited by 13
38 more
  1. 2022The Future of Consumer Edge-AI Computingcited by 12
  2. 2024TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deploymentcited by 11
  3. 2022Towards Battery-Free Machine Learning and Inference in Underwater Environmentscited by 9
  4. 2023ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learningcited by 9
  5. 2023A Survey of Secure Computation Using Trusted Execution Environmentscited by 8
  6. 2024A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakagecited by 8
  7. 2024A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentialitycited by 8
  8. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 6
  9. 2022Shielding Federated Learning Systems against Inference Attacks with ARM TrustZonecited by 5
  10. 2024CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deploymentcited by 5
  11. 2021Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspectivecited by 4
  12. 2022RL-DistPrivacy: Privacy-Aware Distributed Deep Inference for low latency IoT systemscited by 4
  13. 2023All Rivers Run to the Sea: Private Learning with Asymmetric Flowscited by 4
  14. 2022Edge Security: Challenges and Issuescited by 3
  15. 2023Privacy Threats in Stable Diffusion Modelscited by 3
  16. 2024TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Modelscited by 3
  17. 2021Quantifying and Localizing Usable Information Leakage from Neural Network Gradientscited by 2
  18. 2021How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architecturescited by 2
  19. 2023Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environmentscited by 2
  20. 2024TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environmentscited by 2
  21. 2025SecureInfer: Heterogeneous TEE-GPU Architecture for Privacy-Critical Tensors for Large Language Model Deploymentcited by 2
  22. 2022Enhancing the Security & Privacy of Wearable Brain-Computer Interfacescited by 1
  23. 2023Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learningcited by 1
  24. 2024Dataset Condensation Driven Machine Unlearningcited by 1
  25. 2024Towards Secure and Private AI: A Framework for Decentralized Inferencecited by 1
  26. 2026FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolationcited by 1
  27. 2021Privacy and Integrity Preserving Training Using Trusted Hardwarecited by 0
  28. 2022Training privacy-preserving video analytics pipelines by suppressing features that reveal information about private attributescited by 0
  29. 2022Distributed data analyticscited by 0
  30. 2022MixNN: A design for protecting deep learning modelscited by 0
  31. 2023Edge Deep Learning Model Protection via Neuron Authorizationcited by 0
  32. 2023A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inferencecited by 0
  33. 2024Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attackcited by 0
  34. 2024Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devicescited by 0
  35. 2024Protecting Confidentiality, Privacy and Integrity in Collaborative Learningcited by 0
  36. 2025Graph in the Vault: Protecting Edge GNN Inference with Trusted Execution Environmentcited by 0
  37. 2025DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edgecited by 0
  38. 2026Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmapcited by 0

50 most cited of 57 All 57 (JSON)