mlsanityData to 7 Oct 2026

DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware

arXiv 2207.00083 ↗First posted 30 Jun 2022cs.CR cs.AR cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train or infer with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. Cloud systems are vulnerable to attackers that compromise the privacy of data and integrity of computations. Tackling such a challenge requires unifying theoretical privacy algorithms with hardware security capabilities. This paper presents DarKnight, a framework for large DNN training while protecting input privacy and computation integrity. DarKnight relies on cooperative execution between trusted execution environments (TEE) and accelerators, where the TEE provides privacy and integrity verification, while accelerators perform the bulk of the linear algebraic computation to optimize the performance. In particular, DarKnight uses a customized data encoding strategy based on matrix masking to create input obfuscation within a TEE. The obfuscated data is then offloaded to GPUs for fast linear algebraic computation. DarKnight's data obfuscation strategy provides provable data privacy and computation integrity in the cloud servers. While prior works tackle inference privacy and cannot be utilized for training, DarKnight's encoding scheme is designed to support both training and inference.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 37 of its 98 references that are in the map. First posted on arXiv 30 Jun 2022.

Builds on

37 of 98 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  7. 2019Deep Leakage from Gradientscited by 1,004
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  9. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  10. 2015Deep Learning with Limited Numerical Precisioncited by 368
  11. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
  12. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
25 more
  1. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 163
  2. 2015Fixed Point Quantization of Deep Convolutional Networkscited by 141
  3. 2016An Analysis of Deep Neural Network Models for Practical Applicationscited by 114
  4. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 101
  5. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  6. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  7. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  8. 2020InstaHide: Instance-hiding Schemes for Private Distributed Learningcited by 90
  9. 2020Privacy in Deep Learning: A Surveycited by 70
  10. 2018Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacycited by 66
  11. 2020DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environmentscited by 57
  12. 2017SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloudcited by 50
  13. 2015Staleness-aware Async-SGD for Distributed Deep Learningcited by 43
  14. 2019SWALP : Stochastic Weight Averaging in Low-Precision Trainingcited by 40
  15. 2018Chiron: Privacy-preserving Machine Learning as a Servicecited by 38
  16. 2020Is Private Learning Possible with Instance Encoding?cited by 22
  17. 2019Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environmentscited by 17
  18. 2018Efficient Deep Learning on Multi-Source Private Datacited by 16
  19. 2017Leaky Cauldron on the Dark Land: Understanding Memory Side-Channel Hazards in SGXcited by 15
  20. 2017Software Grand Exposure: SGX Cache Attacks Are Practicalcited by 14
  21. 2021Byzantine-Robust and Privacy-Preserving Framework for FedMLcited by 13
  22. 2019Secure Distributed On-Device Learning Networks With Byzantine Adversariescited by 7
  23. 2020GOAT: GPU Outsourcing of Deep Learning Training With Asynchronous Probabilistic Integrity Verification Inside Trusted Execution Environmentcited by 6
  24. 2017An Ontology-based Adaptive Personalized E-learning System, Assisted by Software Agents on Cloud Storagecited by 5
  25. 2021LAORAM: A Look Ahead ORAM Architecture for Training Large Embedding Tablescited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 5; 2025: 2.

13 papers.

Sort:

By area:

  1. 2023No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device MLcited by 21
  2. 2024TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deploymentcited by 11
  3. 2023A Survey of Secure Computation Using Trusted Execution Environmentscited by 8
  4. 2023All Rivers Run to the Sea: Private Learning with Asymmetric Flowscited by 4
  5. 2022DiVa: An Accelerator for Differentially Private Machine Learningcited by 3
  6. 2024TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Modelscited by 3
  7. 2024Tempo: Confidentiality Preservation in Cloud-Based Neural Network Trainingcited by 2
  8. 2025Securing Transformer-based AI Execution via Unified TEEs and Crypto-protected Acceleratorscited by 2
  9. 2024Edge Private Graph Neural Networks with Singular Value Perturbationcited by 1
  10. 2025Towards Confidential and Efficient LLM Inference with Dual Privacy Protectioncited by 1
  11. 2023Edge Deep Learning Model Protection via Neuron Authorizationcited by 0
  12. 2023A Generative Framework for Low-Cost Result Validation of Machine Learning-as-a-Service Inferencecited by 0
1 more
  1. 2024Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devicescited by 0