Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 226

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

PPFL: privacy-preserving federated learning with trusted execution environments

Open access
Mo, Fan, Haddadi, Hamed, Katevas, Kleomenis, Marin, Eduard, Perino, Diego, Kourtellis, Nicolas·2021·Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services

Abstract

We propose and implement a Privacy-preserving Federated Learning ( PPFL ) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end and mobile devices, we utilize TEEs on clients for local training, and on servers for secure aggregation, so that model/gradient updates are hidden from adversaries. Challenged by the limited memory size of current TEEs, we leverage greedy layer-wise training to train each model's layer inside the trusted area until its convergence. The performance evaluation of our implementation shows that PPFL can significantly improve privacy while incurring small system overheads at the client-side. In particular, PPFL can successfully defend the trained model against data reconstruction, property inference, and membership inference attacks. Furthermore, it can achieve comparable model utility with fewer communication rounds (0.54×) and a similar amount of network traffic (1.002×) compared to the standard federated learning of a complete model. This is achieved while only introducing up to ~15% CPU time, ~18% memory usage, and ~21% energy consumption overhead in PPFL's client-side.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3458864.3466628

Cites

18 of 18 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 18 references

Research works printed but not linked: 58

  1. 10.1007/978-3-030-22496-7_9 · DOI
  2. Bagdasaryan , E. , Poursaeed , O. , and Shmatikov , V . Differential privacy has disparate impact on model accuracy . In Advances in Neural Information Processing Systems ( 2019 ), pp. 15479 -- 15488 . Bagdasaryan, E., Poursaeed, O., and Shmatikov, V. Differential privacy has disparate impact on model accuracy. In Advances in Neural Information Processing Systems (2019), pp. 15479--15488.
  3. Belilovsky , E. , Eickenberg , M. , and Oyallon , E . Greedy layerwise learning can scale to imagenet . In International conference on machine learning ( 2019 ), PMLR, pp. 583 -- 593 . Belilovsky, E., Eickenberg, M., and Oyallon, E. Greedy layerwise learning can scale to imagenet. In International conference on machine learning (2019), PMLR, pp. 583--593.
  4. Bengio , Y. , Lamblin , P. , Popovici , D. , and Larochelle , H . Greedy layer-wise training of deep networks. Advances in neural information processing systems 19 ( 2006 ), 153--160. Bengio, Y., Lamblin, P., Popovici, D., and Larochelle, H. Greedy layer-wise training of deep networks. Advances in neural information processing systems 19 (2006), 153--160.
  5. Bonawitz , K. , Eichner , H. , Grieskamp , W. , Huba , D. , Ingerman , A. , Ivanov , V. , Kiddon , C. , Konečnỳ , J. , Mazzocchi , S. , McMahan , H. B. , Towards federated learning at scale: System design . In Conference on Machine Learning and Systems ( 2019 ). Bonawitz, K., Eichner, H., Grieskamp, W., Huba, D., Ingerman, A., Ivanov, V., Kiddon, C., Konečnỳ, J., Mazzocchi, S., McMahan, H. B., et al. Towards federated learning at scale: System design. In Conference on Machine Learning and Systems (2019).
  6. 10.1145/3133956.3133982 · DOI · Paper page
  7. Brownlee , J. A Gentle Introduction to Transfer Learning for Deep Learning , 2019 (accessed November 11, 2020). Brownlee, J. A Gentle Introduction to Transfer Learning for Deep Learning, 2019 (accessed November 11, 2020).
  8. 10.1145/3307650.3322251 · DOI
  9. Chen , J. , Pan , X. , Monga , R. , Bengio , S. , and Jozefowicz , R . Revisiting distributed synchronous sgd . In ICLR Workshop Track ( 2016 ). Chen, J., Pan, X., Monga, R., Bengio, S., and Jozefowicz, R. Revisiting distributed synchronous sgd. In ICLR Workshop Track (2016).
  10. Chen , Z. , Vasilakis , G. , Murdock , K. , Dean , E. , Oswald , D. , and Garcia , F. D . Voltpillager: Hardware-based fault injection attacks against intel SGX enclaves using the SVID voltage scaling interface . In 30th USENIX Security Symposium ( Vancouver, B.C. , Aug. 2021 ). Chen, Z., Vasilakis, G., Murdock, K., Dean, E., Oswald, D., and Garcia, F. D. Voltpillager: Hardware-based fault injection attacks against intel SGX enclaves using the SVID voltage scaling interface. In 30th USENIX Security Symposium (Vancouver, B.C., Aug. 2021).
  11. Costan , V. , and Devadas , S . Intel sgx explained. IACR Cryptol. ePrint Arch . 2016 , 86 (2016), 1--118. Costan, V., and Devadas, S. Intel sgx explained. IACR Cryptol. ePrint Arch. 2016, 86 (2016), 1--118.
  12. Dwork , C. , Roth , A. , The algorithmic foundations of differential privacy . Foundations and Trends in Theoretical Computer Science 9 , 3 -- 4 ( 2014 ), 211--407. Dwork, C., Roth, A., et al. The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science 9, 3--4 (2014), 211--407.
  13. Geiping , J. , Bauermeister , H. , Dröge , H. , and Moeller , M . Inverting gradients-how easy is it to break privacy in federated learning? arXiv preprint arXiv:2003.14053 ( 2020 ). Geiping, J., Bauermeister, H., Dröge, H., and Moeller, M. Inverting gradients-how easy is it to break privacy in federated learning? arXiv preprint arXiv:2003.14053 (2020). · arXiv
  14. Geyer , R. C. , Klein , T. , and Nabi , M . Differentially private federated learning: A client level perspective. arXiv preprint arXiv:1712.07557 ( 2017 ). Geyer, R. C., Klein, T., and Nabi, M. Differentially private federated learning: A client level perspective. arXiv preprint arXiv:1712.07557 (2017). · arXiv
  15. Gu , Z. , Huang , H. , Zhang , J. , Su , D. , Jamjoom , H. , Lamba , A. , Pendarakis , D. , and Molloy , I . Yerbabuena: Securing deep learning inference data via enclave-based ternary model partitioning. arXiv preprint arXiv:1807.00969 ( 2018 ). Gu, Z., Huang, H., Zhang, J., Su, D., Jamjoom, H., Lamba, A., Pendarakis, D., and Molloy, I. Yerbabuena: Securing deep learning inference data via enclave-based ternary model partitioning. arXiv preprint arXiv:1807.00969 (2018). · arXiv
  16. Huang , T. , Lin , W. , Wu , W. , He , L. , Li , K. , and Zomaya , A. Y . An efficiency-boosting client selection scheme for federated learning with fairness guarantee. arXiv preprint arXiv:2011.01783 ( 2020 ). Huang, T., Lin, W., Wu, W., He, L., Li, K., and Zomaya, A. Y. An efficiency-boosting client selection scheme for federated learning with fairness guarantee. arXiv preprint arXiv:2011.01783 (2020). · arXiv
  17. Hunt , T. , Jia , Z. , Miller , V. , Szekely , A. , Hu , Y. , Rossbach , C. J. , and Witchel , E . Telekine: Secure computing with cloud gpus . In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI'20) ( 2020 ), pp. 817 -- 833 . Hunt, T., Jia, Z., Miller, V., Szekely, A., Hu, Y., Rossbach, C. J., and Witchel, E. Telekine: Secure computing with cloud gpus. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI'20) (2020), pp. 817--833.
  18. Hunt , T. , Song , C. , Shokri , R. , Shmatikov , V. , and Witchel , E . Chiron: Privacy-preserving machine learning as a service. arXiv preprint arXiv:1803.05961 ( 2018 ). Hunt, T., Song, C., Shokri, R., Shmatikov, V., and Witchel, E. Chiron: Privacy-preserving machine learning as a service. arXiv preprint arXiv:1803.05961 (2018). · arXiv
  19. 10.1145/3297858.3304021 · DOI
  20. Jayaraman , B. , and Evans , D . Evaluating differentially private machine learning in practice . In 28th USENIX Security Symposium (USENIX Security 19) (Santa Clara, CA , Aug. 2019 ), USENIX Association, pp. 1895--1912. Jayaraman, B., and Evans, D. Evaluating differentially private machine learning in practice. In 28th USENIX Security Symposium (USENIX Security 19) (Santa Clara, CA, Aug. 2019), USENIX Association, pp. 1895--1912.
  21. Kairouz , P. , McMahan , H. B. , Avent , B. , Bellet , A. , Bennis , M. , Bhagoji , A. N. , Bonawitz , K. , Charles , Z. , Cormode , G. , Cummings , R. , Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977 ( 2019 ). Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., et al. Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977 (2019). · arXiv
  22. Katevas , K. , Bagdasaryan , E. , Waterman , J. , Safadieh , M. M. , Birrell , E. , Haddadi , H. , and Estrin , D . Policy-based federated learning. arXiv preprint arXiv:2003.06612 ( 2021 ). Katevas, K., Bagdasaryan, E., Waterman, J., Safadieh, M. M., Birrell, E., Haddadi, H., and Estrin, D. Policy-based federated learning. arXiv preprint arXiv:2003.06612 (2021). · arXiv
  23. Kaya , Y. , Hong , S. , and Dumitras , T . Shallow-deep networks: Understanding and mitigating network overthinking . In International Conference on Machine Learning ( 2019 ), PMLR, pp. 3301 -- 3310 . Kaya, Y., Hong, S., and Dumitras, T. Shallow-deep networks: Understanding and mitigating network overthinking. In International Conference on Machine Learning (2019), PMLR, pp. 3301--3310.
  24. Knauth , T. , Steiner , M. , Chakrabarti , S. , Lei , L. , Xing , C. , and Vij , M . Integrating remote attestation with transport layer security. arXiv preprint arXiv:1801.05863 ( 2018 ). Knauth, T., Steiner, M., Chakrabarti, S., Lei, L., Xing, C., and Vij, M. Integrating remote attestation with transport layer security. arXiv preprint arXiv:1801.05863 (2018). · arXiv
  25. 10.1145/3426745.3431337 · DOI
  26. Krawczyk , H. Sigma : The 'sign-and-mac' approach to authenticated diffiehellman and its use in the ike protocols . In Annual International Cryptology Conference ( 2003 ), Springer , pp. 400 -- 425 . Krawczyk, H. Sigma: The 'sign-and-mac' approach to authenticated diffiehellman and its use in the ike protocols. In Annual International Cryptology Conference (2003), Springer, pp. 400--425.
  27. Krizhevsky , A. , Hinton , G. , Learning multiple layers of features from tiny images. Citeseer ( 2009 ). Krizhevsky, A., Hinton, G., et al. Learning multiple layers of features from tiny images. Citeseer (2009).
  28. Larochelle , H. , Bengio , Y. , Louradour , J. , and Lamblin , P . Exploring strategies for training deep neural networks. Journal of machine learning research 10, 1 ( 2009 ). Larochelle, H., Bengio, Y., Louradour, J., and Lamblin, P. Exploring strategies for training deep neural networks. Journal of machine learning research 10, 1 (2009).
  29. Lee , J. , Jang , J. , Jang , Y. , Kwak , N. , Choi , Y. , Choi , C. , Kim , T. , Peinado , M. , and Kang , B. B . Hacking in Darkness: Return-Oriented Programming against Secure Enclaves . In Proceedings of the 26th USENIX Conference on Security Symposium ( 2017 ), pp. 523 -- 539 . Lee, J., Jang, J., Jang, Y., Kwak, N., Choi, Y., Choi, C., Kim, T., Peinado, M., and Kang, B. B. Hacking in Darkness: Return-Oriented Programming against Secure Enclaves. In Proceedings of the 26th USENIX Conference on Security Symposium (2017), pp. 523--539.
  30. Linaro .org. Open Portable Trusted Execution Environment , 2020 (accessed September 3, 2020). Linaro.org. Open Portable Trusted Execution Environment, 2020 (accessed September 3, 2020).
  31. 10.1109/SP40001.2021.00063 · DOI · Paper page
  32. McMahan , B. , Moore , E. , Ramage , D. , Hampson , S. , and y Arcas , B. A. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics (2017) , PMLR , pp. 1273 -- 1282 . McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics (2017), PMLR, pp. 1273--1282.
  33. McMahan , H. B. , Ramage , D. , Talwar , K. , and Zhang , L . Learning differentially private recurrent language models . In International Conference on Learning Representations ( 2018 ). McMahan, H. B., Ramage, D., Talwar, K., and Zhang, L. Learning differentially private recurrent language models. In International Conference on Learning Representations (2018).
  34. Microsoft . Open Enclave SDK , 2020 (accessed Decemenber 4, 2020). Microsoft. Open Enclave SDK, 2020 (accessed Decemenber 4, 2020).
  35. Mo , F. , Borovykh , A. , Malekzadeh , M. , Haddadi , H. , and Demetriou , S . Layer-wise characterization of latent information leakage in federated learning . ICLR Distributed and Private Machine Learning workshop ( 2021 ). Mo, F., Borovykh, A., Malekzadeh, M., Haddadi, H., and Demetriou, S. Layer-wise characterization of latent information leakage in federated learning. ICLR Distributed and Private Machine Learning workshop (2021).
  36. Mo , F. , and Haddadi , H . Efficient and private federated learning using tee . In EuroSys ( 2019 ). Mo, F., and Haddadi, H. Efficient and private federated learning using tee. In EuroSys (2019).
  37. 10.1145/3386901.3388946 · DOI · Paper page
  38. Monsoon . Monsoon solutions inc. home page. https://www.msoon.com/ , 2020 (accessed November 12, 2020). Monsoon. Monsoon solutions inc. home page. https://www.msoon.com/, 2020 (accessed November 12, 2020).
  39. 10.1145/2046660.2046682 · DOI · Paper page
  40. 10.1109/SP.2019.00065 · DOI · Paper page
  41. 10.5555/3241094.3241143 · doi:10.5555/3241094.3241143
  42. Paladi , N. , Karlsson , L. , and Elbashir , K . Trust Anchors in Software Defined Networks. In Computer Security ( 2018 ), pp. 485 -- 504 . Paladi, N., Karlsson, L., and Elbashir, K. Trust Anchors in Software Defined Networks. In Computer Security (2018), pp. 485--504.
  43. Sablayrolles , A. , Douze , M. , Schmid , C. , Ollivier , Y. , and Jégou , H . White-box vs black-box: Bayes optimal strategies for membership inference . In International Conference on Machine Learning ( 2019 ), pp. 5558 -- 5567 . Sablayrolles, A., Douze, M., Schmid, C., Ollivier, Y., and Jégou, H. White-box vs black-box: Bayes optimal strategies for membership inference. In International Conference on Machine Learning (2019), pp. 5558--5567.
  44. Sagheer , A. , and Kotb , M . Unsupervised pre-training of a deep lstm-based stacked autoencoder for multivariate time series forecasting problems. Scientific reports 9, 1 ( 2019 ), 1--16. Sagheer, A., and Kotb, M. Unsupervised pre-training of a deep lstm-based stacked autoencoder for multivariate time series forecasting problems. Scientific reports 9, 1 (2019), 1--16.
  45. 10.1109/SP.2015.10 · DOI · Paper page
  46. Simonyan , K. , and Zisserman , A . Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Simonyan, K., and Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014). · arXiv
  47. Subramani , P. , Vadivelu , N. , and Kamath , G . Enabling fast differentially private sgd via just-in-time compilation and vectorization. arXiv preprint arXiv:2010.09063 ( 2020 ). Subramani, P., Vadivelu, N., and Kamath, G. Enabling fast differentially private sgd via just-in-time compilation and vectorization. arXiv preprint arXiv:2010.09063 (2020). · arXiv
  48. Sun , Z. , Kairouz , P. , Suresh , A. T. , and McMahan , H. B. Can you really backdoor federated learning? arXiv preprint arXiv:1911.07963 ( 2019 ). Sun, Z., Kairouz, P., Suresh, A. T., and McMahan, H. B. Can you really backdoor federated learning? arXiv preprint arXiv:1911.07963 (2019). · arXiv
  49. Testuggine , D. , and Mironov , I . Introducing Opacus: A high-speed library for training PyTorch models with differential privacy , 2020 (accessed January 1, 2021). Testuggine, D., and Mironov, I. Introducing Opacus: A high-speed library for training PyTorch models with differential privacy, 2020 (accessed January 1, 2021).
  50. 10.4018/978-1-60566-766-9.ch011 · DOI · Paper page
  51. Tramèr , F. , and Boneh , D . Slalom: Fast, verifiable and private execution of neural networks in trusted hardware . In International Conference on Learning Representations (ICLR) ( 2019 ). Tramèr, F., and Boneh, D. Slalom: Fast, verifiable and private execution of neural networks in trusted hardware. In International Conference on Learning Representations (ICLR) (2019).
  52. Van Bulck , Jo and Oswald, David and Marin, Eduard and Aldoseri, Abdulla and Garcia, Flavio D. and Piessens , Frank. A Tale of Two Worlds: Assessing the Vulnerability of Enclave Shielding Runtimes. In Proceedings of the ACM SIGSAC Conference on Computer and Communications Security (CCS) ( 2019 ), pp. 1741 -- 1758 . Van Bulck, Jo and Oswald, David and Marin, Eduard and Aldoseri, Abdulla and Garcia, Flavio D. and Piessens, Frank. A Tale of Two Worlds: Assessing the Vulnerability of Enclave Shielding Runtimes. In Proceedings of the ACM SIGSAC Conference on Computer and Communications Security (CCS) (2019), pp. 1741--1758.
  53. Wang , H. , Yurochkin , M. , Sun , Y. , Papailiopoulos , D. , and Khazaeni , Y . Federated learning with matched averaging. arXiv preprint arXiv:2002.06440 ( 2020 ). Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., and Khazaeni, Y. Federated learning with matched averaging. arXiv preprint arXiv:2002.06440 (2020). · arXiv
  54. 10.1109/CVPR42600.2020.00220 · DOI
  55. 10.1109/INFOCOM41043.2020.9155414 · DOI
  56. 10.1145/3411495.3421352 · DOI
  57. 10.1145/3319535.3363205 · DOI
  58. Zhu , L. , Liu , Z. , and Han , S . Deep leakage from gradients . In Advances in Neural Information Processing Systems ( 2019 ), pp. 14774 -- 14784 . Zhu, L., Liu, Z., and Han, S. Deep leakage from gradients. In Advances in Neural Information Processing Systems (2019), pp. 14774--14784.

Cited by

See all 226

Metadata

Authors
Mo, F., Haddadi, H., Katevas, K., Marin, E., Perino, D., & Kourtellis, N.
Venue
Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services
Publisher
ACM
Published
2021-06-24
Pages
94-108
OpenAlex
W3176786489
Cited by
226
References
18
FWCI
18.26
Type
conference paper
Language
en
Open access
green
Funders
  • Horizon 2020 Framework Programme (830927; 871793; 871370)
  • Engineering and Physical Sciences Research Council (EP/N028260/1; EP/R03351X/1)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: PPFL: privacy-preserving federated learning with trusted execution environments. https://app.cochat.ai/papers/10.1145/3458864.3466628
The paper
Mo, F., Haddadi, H., Katevas, K., Marin, E., Perino, D., & Kourtellis, N. (2021). PPFL: privacy-preserving federated learning with trusted execution environments. Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services. https://doi.org/10.1145/3458864.3466628

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.