Toward Secure and Privacy-Preserving Distributed Deep Learning in Fog-Cloud Computing
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Fog-cloud computing promises many new vertical service areas beyond simple data communication, storing, and processing. Among them, distributed deep learning (DDL) across fog-cloud computing environment is one of the most popular applications due to its high efficiency and scalability. Compared with the centralized deep learning, DDL can provide better privacy protection with training only on sharing parameters. Nevertheless, when DDL meets fog-cloud computing, it still faces two major security challenges: 1) how to protect users' privacy from being leaked to other internal participants in the training process and 2) how to guarantee users' identities from being forged by external adversaries. To combat them, several approaches have been proposed via various technologies. Nevertheless, those approaches suffer from drawbacks in terms of security, efficiency, and functionality, and cannot guarantee the legitimacy of participants' identities during training. In this article, we propose a secure and privacy-preserving DDL (SPDDL) for fog-cloud computing. Compared with the state-of-the-art works, our proposal achieves a better tradeoff between security, efficiency, and functionality. In addition, our SPDDL can guarantee the unforgeability of users' identities against external adversaries. Extensive experimental results indicate the practical feasibility and high efficiency of our SPDDL.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Public-Key Cryptosystems Based on Composite Degree Residuosity Classes
Paillier, P. (2007) · Lecture Notes in Computer Science · doi:10.1007/3-540-48910-x_16 · Cited by 7,250
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · cited 1×
“State-ofthe-art research [9] has demonstrated that in the DDL-based framework, the user’s private information may be leaked to other internal participants through even a small partition of leaked parameters.”
BackgroundPractical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956 · cited 9×
“and communication overhead, the SMC-based PPML [12] is compared with our SPDDL.”
BackgroundMethodResultInfluentialGoldreich, O., Micali, S., & Wigderson, A. (1987) · Proceedings of the nineteenth annual ACM conference on Theory of computing - STOC '87 · doi:10.1145/28395.28420 · Cited by 3,590
Protocols for secure computations
Yao, A. C. (1982) · 23rd Annual Symposium on Foundations of Computer Science (sfcs 1982) · doi:10.1109/sfcs.1982.38 · Cited by 3,306
Protocols for secure computations
Yao, A. C.-C. (1982) · doi:10.1109/sfcs.1982.88 · Cited by 2,696
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 7×
“Similar to Shokri and Shmatikov’s scheme [38], Abadi et al.”
BackgroundResultInfluentialOn lattices, learning with errors, random linear codes, and cryptography
Regev, O. (2009) · Journal of the ACM · doi:10.1145/1568318.1568324 · Cited by 2,315
SecureML: A System for Scalable Privacy-Preserving Machine Learning
Mohassel, P., & Zhang, Y. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.12 · Cited by 1,936 · cited 3×
“For providing an efficient secure learning model, Mohassel and Zhang [37] proposed a privacy-preserving machine learning, where they exploit two noncolluding servers to achieve secure two-party computation (2PC).”
MethodPrivacy-Preserving Deep Learning via Additively Homomorphic Encryption
Phong, L. T., Aono, Y., Hayashi, T., Wang, L., & Moriai, S. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2787987 · Cited by 1,662 · cited 6×
“Focusing on security, our scheme holds threshold encryption property and does not need to balance accuracy and privacy, both of which make our scheme more secure than AHE-based methods [20], [21] and DP-based methods [22]–[25].”
BackgroundMethodInfluentialDeep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Perez-Cruz, F. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134012 · Cited by 1,377 · cited 3×
“Besides, their schemes [22], [38] are vulnerable if adversaries are allowed to train a generative adversarial network (GAN) [39] to attack the protocol.”
BackgroundMultiparty Computation from Somewhat Homomorphic Encryption
Damgård, I., Pastro, V., Smart, N., & Zakarias, S. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-32009-5_38 · Cited by 1,331 · cited 1×
“Generic SMC-based methods are mainly based on Yao’s GC [14], [43]–[46] and SS [47], [48].”
MethodLearning Differentially Private Recurrent Language Models
McMahan, H. B., Ramage, D., Talwar, K., & Zhang, L. (2017) · arXiv · doi:10.48550/arxiv.1710.06963 · Cited by 849
Verifynet: Secure and verifiable federated learning
Xu, G., Li, H., Liu, S., Yang, K., & Lin, X. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2929409 · Cited by 839
Self-citationSecuring Fog Computing for Internet of Things Applications: Challenges and Solutions
Ni, J., Zhang, K., Lin, X., & Shen, X. (2018) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2762345 · Cited by 659 · cited 1×
“” Based on the decentralized computing architecture, distributed deep learning (DDL) has been properly applied in IoT and supplied with diverse scenarios, such as autonomous vehicles [3], [4], smart grid [5], [6], e-health [7], [8], etc.”
BackgroundEfficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence
Hao, M., Li, H., Luo, X., Xu, G., Yang, H., & Liu, S. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2945367 · Cited by 569 · cited 1×
“stochastic gradient descent (SGD) [11], [27], [28].”
Self-citationEvaluating Differentially Private Machine Learning in Practice
Jayaraman, B., & Evans, D. (2019) · arXiv · doi:10.48550/arxiv.1902.08874 · Cited by 265
Security and Privacy Issues in Deep Learning
Bae, H., Jang, J., Jung, D., Jang, H., Ha, H., Lee, H., & Yoon, S. (2018) · arXiv · doi:10.48550/arxiv.1807.11655 · Cited by 56 · cited 2×
“Additionally, HE-based DDL [11], [13] utilizes fully HE (FHE) or additive HE (AHE) to construct the privacy-preserving protocol.”
BackgroundMethod
Cited by
Privacy-Enhanced Federated Learning Against Poisoning Adversaries
Liu, X., Li, H., Xu, G., Chen, Z., Huang, X., & Lu, R. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3108434 · Cited by 351
Self-citationAkter, M., Moustafa, N., Lynar, T., & Razzak, I. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3192648 · Cited by 128
“According to recent studies, federated learning as distributed deep learning (DDL) can provide better privacy protection than centralised deep learning because it only trains on shareable parameters [22].”
BackgroundFederated Learning in Robotic and Autonomous Systems
Xianjia, Y., Queralta, J. P., Heikkonen, J., & Westerlund, T. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.07.041 · Cited by 79
Metadata
- Authors
- Li, Y., Li, H., Xu, G., Xiang, T., Huang, X., & Lu, R.
- Venue
- IEEE Internet of Things Journal
- Published
- 2020-12
- Volume
- 7
- Issue
- 12
- Pages
- 11460-11472
- ISSN
- 2327-4662 (ISSN-L)
- 2372-2541
- OpenAlex
- W3046112435
- Cited by
- 65
- References
- 18
- FWCI
- 3.13
- Type
- journal article
- Language
- en
- Open access
- closed
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
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.