mlsanityData to 7 Oct 2026

Protecting Confidentiality, Privacy and Integrity in Collaborative Learning

arXiv 2412.08534 ↗First posted 11 Dec 2024cs.DC cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

A collaboration between dataset owners and model owners is needed to facilitate effective machine learning (ML) training. During this collaboration, however, dataset owners and model owners want to protect the confidentiality of their respective assets (i.e., datasets, models and training code), with the dataset owners also caring about the privacy of individual users whose data is in their datasets. Existing solutions either provide limited confidentiality for models and training code, or suffer from privacy issues due to collusion. We present Citadel++, a collaborative ML training system designed to simultaneously protect the confidentiality of datasets, models and training code as well as the privacy of individual users. Citadel++ enhances differential privacy mechanisms to safeguard the privacy of individual user data while maintaining model utility. By employing Virtual Machine-level Trusted Execution Environments (TEEs) as well as the improved sandboxing and integrity mechanisms through OS-level techniques, Citadel++ effectively preserves the confidentiality of datasets, models and training code, and enforces our privacy mechanisms even when the models and training code have been maliciously designed. Our experiments show that Citadel++ provides model utility and performance while adhering to the confidentiality and privacy requirements of dataset owners and model owners, outperforming the state-of-the-art privacy-preserving training systems by up to 543x on CPU and 113x on GPU TEEs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 125 references that are in the map. First posted on arXiv 11 Dec 2024.

Builds on

39 of 125 references.

References · 39

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  6. 2019Deep Leakage from Gradientscited by 1,004
  7. 2021Membership Inference Attacks From First Principlescited by 839
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  9. 2017Renyi Differential Privacycited by 643
  10. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  11. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  12. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
27 more
  1. 2019Differentially Private Learning with Adaptive Clippingcited by 218
  2. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 216
  3. 2021Numerical Composition of Differential Privacycited by 174
  4. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 101
  5. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  6. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 89
  7. 2020FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learningcited by 74
  8. 2022Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streamscited by 59
  9. 2020DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environmentscited by 57
  10. 2018Chiron: Privacy-preserving Machine Learning as a Servicecited by 38
  11. 2020BLAZE: Blazing Fast Privacy-Preserving Machine Learningcited by 32
  12. 2019Trident: Efficient 4PC Framework for Privacy Preserving Machine Learningcited by 26
  13. 2022Differentially private training of residual networks with scale normalisationcited by 26
  14. 2020POSEIDON: Privacy-Preserving Federated Neural Network Learningcited by 23
  15. 2021Not all noise is accounted equally: How differentially private learning benefits from large sampling ratescited by 21
  16. 2018Efficient Deep Learning on Multi-Source Private Datacited by 16
  17. 2021Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGXcited by 14
  18. 2021secureTF: A Secure TensorFlow Frameworkcited by 12
  19. 2016Inferring Fine-grained Control Flow Inside SGX Enclaves with Branch Shadowingcited by 10
  20. 2020GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learningcited by 9
  21. 2021Tetrad: Actively Secure 4PC for Secure Training and Inferencecited by 8
  22. 2024DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-trainingcited by 7
  23. 2024WeSee: Using Malicious #VC Interrupts to Break AMD SEV-SNPcited by 4
  24. 2021SecFL: Confidential Federated Learning using TEEscited by 3
  25. 2024Trustworthy confidential virtual machines for the massescited by 2
  26. 2024Cabin: Confining Untrusted Programs within Confidential VMscited by 2
  27. 2024Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumptioncited by 1

Built on by

Not cited yet.