Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 191

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

DarkneTZ: towards model privacy at the edge using trusted execution environments

Open access
Mo, Fan, Shamsabadi, Ali Shahin, Katevas, Kleomenis, Demetriou, Soteris, Leontiadis, Ilias, Cavallaro, Andrea, Haddadi, Hamed·2020·Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services

Abstract

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).

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 · 10.1145/3386901.3388946

Cites

13 of 13 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 13 references

Research works printed but not linked: 52

  1. 10.1145/2976749.2978318 · DOI · Paper page
  2. Hervé Abdi and Lynne J Williams . 2010. Tukey's honestly significant difference (HSD) test. Encyclopedia of Research Design . Thousand Oaks, CA : Sage ( 2010 ), 1--5. Hervé Abdi and Lynne J Williams. 2010. Tukey's honestly significant difference (HSD) test. Encyclopedia of Research Design. Thousand Oaks, CA: Sage (2010), 1--5.
  3. 10.1145/3214303 · DOI · Paper page
  4. Francis Akowuah , Amit Ahlawat , and Wenliang Du . 2018 . Protecting Sensitive Data in Android SQLite Databases Using TrustZone . In Proceedings of the International Conference on Security and Management (SAM). The Steering Committee of The World Congress in Computer Science, 227--233 . Francis Akowuah, Amit Ahlawat, and Wenliang Du. 2018. Protecting Sensitive Data in Android SQLite Databases Using TrustZone. In Proceedings of the International Conference on Security and Management (SAM). The Steering Committee of The World Congress in Computer Science, 227--233.
  5. A Arm . 2009. Security technology-building a secure system using TrustZone technology. ARM Technical White Paper ( 2009 ). A Arm. 2009. Security technology-building a secure system using TrustZone technology. ARM Technical White Paper (2009).
  6. 10.14722/ndss.2019.23448 · DOI
  7. Rich Caruana Steve Lawrence and C Lee Giles. 2001. Overfitting in neural nets: Backpropagation conjugate gradient and early stopping. In Advances in Neural Information Processing Systems. 402--408. Rich Caruana Steve Lawrence and C Lee Giles. 2001. Overfitting in neural nets: Backpropagation conjugate gradient and early stopping. In Advances in Neural Information Processing Systems. 402--408.
  8. Victor Costan and Srinivas Devadas . 2016 . Intel SGX Explained . IACR Cryptology ePrint Archive 2016 , 086 (2016), 1 -- 118 . Victor Costan and Srinivas Devadas. 2016. Intel SGX Explained. IACR Cryptology ePrint Archive 2016, 086 (2016), 1--118.
  9. Pan Dong , Alan Burns , Zhe Jiang , and Xiangke Liao . 2018 . TZDKS: A New TrustZone-Based Dual-Criticality System with Balanced Performance. In 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA) . IEEE , 59--64. Pan Dong, Alan Burns, Zhe Jiang, and Xiangke Liao. 2018. TZDKS: A New TrustZone-Based Dual-Criticality System with Balanced Performance. In 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA). IEEE, 59--64.
  10. 10.1109/CVPR.2016.522 · DOI · Paper page
  11. Cynthia Dwork Aaron Roth etal 2014. The algorithmic foundations of differential privacy. Foundations and Trends® in Theoretical Computer Science 9 3-4 (2014) 211--407. Cynthia Dwork Aaron Roth et al. 2014. The algorithmic foundations of differential privacy. Foundations and Trends ® in Theoretical Computer Science 9 3-4 (2014) 211--407. · DOI · Paper page
  12. 10.1145/2810103.2813677 · DOI · Paper page
  13. Zhongshu Gu , Heqing Huang , Jialong Zhang , Dong Su , Hani Jamjoom , Ankita Lamba , Dimitrios Pendarakis , and Ian Molloy . 2018. YerbaBuena: Securing Deep Learning Inference Data via Enclave-based Ternary Model Partitioning. arXiv preprint arXiv:1807.00969 ( 2018 ). Zhongshu Gu, Heqing Huang, Jialong Zhang, Dong Su, Hani Jamjoom, Ankita Lamba, Dimitrios Pendarakis, and Ian Molloy. 2018. YerbaBuena: Securing Deep Learning Inference Data via Enclave-based Ternary Model Partitioning. arXiv preprint arXiv:1807.00969 (2018). · arXiv
  14. Song Han , Huizi Mao , and William J Dally . 2015 . Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 . In International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1510 .00149 Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149. In International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1510.00149 · arXiv
  15. Lucjan Hanzlik , Yang Zhang , Kathrin Grosse , Ahmed Salem , Max Augustin , Michael Backes , and Mario Fritz . 2018 . Mlcapsule: Guarded offline deployment of machine learning as a service. arXiv preprint arXiv:1808.00590 (2018). Lucjan Hanzlik, Yang Zhang, Kathrin Grosse, Ahmed Salem, Max Augustin, Michael Backes, and Mario Fritz. 2018. Mlcapsule: Guarded offline deployment of machine learning as a service. arXiv preprint arXiv:1808.00590 (2018). · arXiv
  16. Andrew G Howard , Menglong Zhu , Bo Chen , Dmitry Kalenichenko , Weijun Wang , Tobias Weyand , Marco Andreetto , and Hartwig Adam . 2017 . Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017). Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017). · arXiv
  17. 10.1109/CVPR.2017.243 · DOI · Paper page
  18. Tyler Hunt , Congzheng Song , Reza Shokri , Vitaly Shmatikov , and Emmett Witchel . 2018 . Chiron: Privacy-preserving Machine Learning as a Service. arXiv preprint arXiv:1803.05961 (2018). Tyler Hunt, Congzheng Song, Reza Shokri, Vitaly Shmatikov, and Emmett Witchel. 2018. Chiron: Privacy-preserving Machine Learning as a Service. arXiv preprint arXiv:1803.05961 (2018). · arXiv
  19. Nick Hynes , Raymond Cheng , and Dawn Song . 2018. Efficient deep learning on multi-source private data. arXiv preprint arXiv:1807.06689 ( 2018 ). Nick Hynes, Raymond Cheng, and Dawn Song. 2018. Efficient deep learning on multi-source private data. arXiv preprint arXiv:1807.06689 (2018). · arXiv
  20. Forrest N Iandola , Song Han , Matthew W Moskewicz , Khalid Ashraf , William J Dally , and Kurt Keutzer . 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < ; 0.5 MB model size. arXiv preprint arXiv:1602.07360 ( 2016 ). Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016). · arXiv
  21. Bargav Jayaraman and David Evans . 2019 . Evaluating Differentially Private Machine Learning in Practice. In 28th USENIX Security Symposium (USENIX Security 19) . USENIX Association, Santa Clara, CA , 1895--1912. https://www.usenix.org/conference/usenixsecurity19/presentation/jayaraman Bargav Jayaraman and David Evans. 2019. Evaluating Differentially Private Machine Learning in Practice. In 28th USENIX Security Symposium (USENIX Security 19). USENIX Association, Santa Clara, CA, 1895--1912. https://www.usenix.org/conference/usenixsecurity19/presentation/jayaraman
  22. 10.1145/3319535.3363201 · DOI · Paper page
  23. 10.1007/978-3-540-45146-4_24 · DOI · Paper page
  24. Yann LeCun , Yoshua Bengio , and Geoffrey Hinton . 2015. Deep learning. nature 521, 7553 ( 2015 ), 436--444. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature 521, 7553 (2015), 436--444.
  25. 10.1145/2508859.2516686 · DOI
  26. 10.1145/3319535.3363279 · DOI
  27. 10.1145/2046660.2046682 · DOI · Paper page
  28. Milad Nasr , Reza Shokri , and Amir Houmansadr . 2019 . Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks . In Proceedings of 40th IEEE Symposium on Security & Privacy. IEEE. Milad Nasr, Reza Shokri, and Amir Houmansadr. 2019. Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks. In Proceedings of 40th IEEE Symposium on Security & Privacy. IEEE.
  29. Olga Ohrimenko , Felix Schuster , Cedric Fournet , Aastha Mehta , Sebastian Nowozin , Kapil Vaswani , and Manuel Costa . 2016 . Oblivious Multi-Party Machine Learning on Trusted Processors. In 25th USENIX Security Symposium (USENIX Security 16) . USENIX Association, Austin, TX, 619--636. https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/ohrimenko Olga Ohrimenko, Felix Schuster, Cedric Fournet, Aastha Mehta, Sebastian Nowozin, Kapil Vaswani, and Manuel Costa. 2016. Oblivious Multi-Party Machine Learning on Trusted Processors. In 25th USENIX Security Symposium (USENIX Security 16). USENIX Association, Austin, TX, 619--636. https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/ohrimenko
  30. Seyed Ali Osia , Ali Shahin Shamsabadi , Ali Taheri, Kleomenis Katevas, Sina Sajadmanesh, Hamid R Rabiee, Nicholas D Lane, and Hamed Haddadi. 2020 . A hybrid deep learning architecture for privacy-preserving mobile analytics. IEEE Internet of Things Journal ( 2020). Seyed Ali Osia, Ali Shahin Shamsabadi, Ali Taheri, Kleomenis Katevas, Sina Sajadmanesh, Hamid R Rabiee, Nicholas D Lane, and Hamed Haddadi. 2020. A hybrid deep learning architecture for privacy-preserving mobile analytics. IEEE Internet of Things Journal (2020).
  31. 10.1109/MC.2018.2381113 · DOI
  32. Heejin Park Shuang Zhai Long Lu and Felix Xiaozhu Lin. 2019. StreamBox-TZ: secure stream analytics at the edge with TrustZone. In 2019 {USENIX} Annual Technical Conference 19. 537--554. Heejin Park Shuang Zhai Long Lu and Felix Xiaozhu Lin. 2019. StreamBox-TZ: secure stream analytics at the edge with TrustZone. In 2019 { USENIX } Annual Technical Conference 19. 537--554.
  33. Adam Paszke , Sam Gross , Soumith Chintala , Gregory Chanan , Edward Yang , Zachary DeVito , Zeming Lin , Alban Desmaison , Luca Antiga , and Adam Lerer . 2017 . Automatic Differentiation in PyTorch. In NIPS Autodiff Workshop. Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic Differentiation in PyTorch. In NIPS Autodiff Workshop.
  34. Adityanarayanan Radhakrishnan , Mikhail Belkin , and Caroline Uhler . 2018. Downsampling leads to Image Memorization in Convolutional Autoencoders. arXiv preprint arXiv:1810.10333 ( 2018 ). Adityanarayanan Radhakrishnan, Mikhail Belkin, and Caroline Uhler. 2018. Downsampling leads to Image Memorization in Convolutional Autoencoders. arXiv preprint arXiv:1810.10333 (2018). · arXiv
  35. Md Atiqur Rahman , Tanzila Rahman , Robert Laganière , Noman Mohammed , and Yang Wang . 2018 . Membership Inference Attack against Differentially Private Deep Learning Model . Transactions on Data Privacy 11 , 1 (2018), 61 -- 79 . Md Atiqur Rahman, Tanzila Rahman, Robert Laganière, Noman Mohammed, and Yang Wang. 2018. Membership Inference Attack against Differentially Private Deep Learning Model. Transactions on Data Privacy 11, 1 (2018), 61--79.
  36. Ahmed Salem , Yang Zhang , Mathias Humbert , Pascal Berrang , Mario Fritz , and Michael Backes . 2018 . Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models. arXiv preprint arXiv:1806.01246 . In Network and Distributed Systems Security (NDSS) Symposium 2018 . https://arxiv.org/abs/1806.01246 Ahmed Salem, Yang Zhang, Mathias Humbert, Pascal Berrang, Mario Fritz, and Michael Backes. 2018. Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models. arXiv preprint arXiv:1806.01246. In Network and Distributed Systems Security (NDSS) Symposium 2018. https://arxiv.org/abs/1806.01246 · arXiv
  37. 10.1109/CVPR.2015.7298594 · DOI · Paper page
  38. Shruti Tople , Karan Grover , Shweta Shinde , Ranjita Bhagwan , and Ramachandran Ramjee . 2018 . Privado: Practical and secure DNN inference. arXiv preprint arXiv:1810.00602 (2018). Shruti Tople, Karan Grover, Shweta Shinde, Ranjita Bhagwan, and Ramachandran Ramjee. 2018. Privado: Practical and secure DNN inference. arXiv preprint arXiv:1810.00602 (2018). · arXiv
  39. Florian Tramèr and Dan Boneh . 2019 . Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware. arXiv preprint arXiv:1806.03287 . In International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1806 .03287 Florian Tramèr and Dan Boneh. 2019. Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware. arXiv preprint arXiv:1806.03287. In International Conference on Learning Representations (ICLR). https://arxiv.org/abs/1806.03287 · arXiv
  40. 10.1109/CVPR.2019.00881 · DOI · Paper page
  41. 10.1145/3133956.3134038 · DOI · Paper page
  42. 10.1109/TIFS.2019.2897874 · DOI · Paper page
  43. 10.1145/3308558.3313591 · DOI · Paper page
  44. 10.1145/3319535.3354261 · DOI · Paper page
  45. 10.1145/3210240.3210338 · DOI
  46. Jason Yosinski , Jeff Clune , Anh Nguyen , Thomas Fuchs , and Hod Lipson . 2015 . Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579 . In Deep Learning Workshop in International Conference on Machine Learning. https://arxiv.org/abs/1506 .06579 Jason Yosinski, Jeff Clune, Anh Nguyen, Thomas Fuchs, and Hod Lipson. 2015. Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579. In Deep Learning Workshop in International Conference on Machine Learning. https://arxiv.org/abs/1506.06579 · arXiv
  47. 10.1109/SP.2019.00019 · DOI · Paper page
  48. 10.1007/978-3-319-10590-1_53 · DOI · Paper page
  49. 10.1109/COMST.2019.2904897 · DOI · Paper page
  50. Shengjia Zhao , Jiaming Song , and Stefano Ermon . 2017 . Learning hierarchical features from deep generative models . In International Conference on Machine Learning. 4091--4099 . Shengjia Zhao, Jiaming Song, and Stefano Ermon. 2017. Learning hierarchical features from deep generative models. In International Conference on Machine Learning. 4091--4099.
  51. 10.1145/3319535.3363205 · DOI
  52. Ligeng Zhu Zhijian Liu and Song Han. 2019. Deep leakage from gradients. In Advances in Neural Information Processing Systems. 14747--14756. Ligeng Zhu Zhijian Liu and Song Han. 2019. Deep leakage from gradients. In Advances in Neural Information Processing Systems. 14747--14756.

Cited by

See all 191

Metadata

Authors
Mo, F., Shamsabadi, A. S., Katevas, K., Demetriou, S., Leontiadis, I., Cavallaro, A., & Haddadi, H.
Venue
Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services
Publisher
ACM
Published
2020-06-15
Pages
161-174
OpenAlex
W3016075089
Cited by
191
References
13
FWCI
8.67
Type
conference paper
Language
en
Open access
green
Funders
  • EPSRC Databox (EP/N028260/1)
  • EPSRC DADA (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: DarkneTZ: towards model privacy at the edge using trusted execution environments. https://app.cochat.ai/papers/10.1145/3386901.3388946
The paper
Mo, F., Shamsabadi, A. S., Katevas, K., Demetriou, S., Leontiadis, I., Cavallaro, A., & Haddadi, H. (2020). DarkneTZ: towards model privacy at the edge using trusted execution environments. Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services. https://doi.org/10.1145/3386901.3388946

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.