Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Oct 29;20(21):6153.
doi: 10.3390/s20216153.

Privacy-Preserving Distributed Analytics in Fog-Enabled IoT Systems

Liang Zhao  1
Affiliations

Privacy-Preserving Distributed Analytics in Fog-Enabled IoT Systems

Liang Zhao. Sensors (Basel). .

Abstract

The Internet of Things (IoT) has evolved significantly with advances in gathering data that can be extracted to provide knowledge and facilitate decision-making processes. Currently, IoT data analytics encountered challenges such as growing data volumes collected by IoT devices and fast response requirements for time-sensitive applications in which traditional Cloud-based solution is unable to meet due to bandwidth and high latency limitations. In this paper, we develop a distributed analytics framework for fog-enabled IoT systems aiming to avoid raw data movement and reduce latency. The distributed framework leverages the computational capacities of all the participants such as edge devices and fog nodes and allows them to obtain the global optimal solution locally. To further enhance the privacy of data holders in the system, a privacy-preserving protocol is proposed using cryptographic schemes. Security analysis was conducted and it verified that exact private information about any edge device's raw data would not be inferred by an honest-but-curious neighbor in the proposed secure protocol. In addition, the accuracy of solution is unaffected in the secure protocol comparing to the proposed distributed algorithm without encryption. We further conducted experiments on three case studies: seismic imaging, diabetes progression prediction, and Enron email classification. On seismic imaging problem, the proposed algorithm can be up to one order of magnitude faster than the benchmarks in reaching the optimal solution. The evaluation results validate the effectiveness of the proposed methodology and demonstrate its potential to be a promising solution for data analytics in fog-enabled IoT systems.

Keywords: distributed analytics; fog computing; internet of things; privacy-preserving.

PubMed Disclaimer

Conflict of interest statement

The author declares no conflict of interest.

Figures

Figure 1
Figure 1
Fog-enabled IoT system infrastructure [7].
Figure 2
Figure 2
An illustrative example of executing Algorithms 1 and 2.
Figure 3
Figure 3
An example of secure interaction for fog nodes in Algorithm 3.
Figure 4
Figure 4
An example of secure interaction for edge devices in Algorithm 4.
Figure 5
Figure 5
An example of the CORE GUI.
Figure 6
Figure 6
Procedures of seismic imaging. The first step is event localization (a), then ray tracing (b), and the final step is tomography inversion (c). We focus on the last step only in this scenario since it is the main computation stage.
Figure 7
Figure 7
Seismic imaging problem with comparing the accuracy of the proposed distributed algorithm with or without encryption. (a) and (b) compare the performance of proposed algorithm with and without encryption in terms of objective value and disagreement, respectively.
Figure 8
Figure 8
Seismic imaging problem with convergence behavior comparison. (a) and (b) compare the performance of proposed algorithm with the benchmarks in terms of objective value and disagreement, respectively.
Figure 9
Figure 9
Seismic imaging problem with tomography results comparison. The dimension of the tomography results is 64×64 and hence there are 64 blocks along the vertical and horizontal axes, respectively (a–c).
Figure 10
Figure 10
Diabetes progression prediction with 20 edge devices and 5 fog nodes. (a) and (b) compare the performance of proposed algorithm with the benchmarks in terms of training and testing error, respectively.
Figure 11
Figure 11
Diabetes progression prediction with 40 edge devices and 10 fog nodes. (a) and (b) compare the performance of proposed algorithm with the benchmarks in terms of training and testing error, respectively.
Figure 12
Figure 12
Enron Spam Email Classification with 100 edge devices and five fog nodes. The average model obtained from five fog nodes is illustrated. The latency for communication is set to 5 ms, and bandwidth is set to 10 mbps. (a) and (b) depict the performance of proposed algorithm in terms of training error and training log loss, respectively.
Figure 13
Figure 13
Enron Spam Email Classification with various numbers of fog nodes: 5, 10, and 20. (a) and (b) illustrate the performance of proposed algorithm in terms of training error and training log loss, respectively.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Evans D. The Internet of Things: How the Next Evolution of the Internet Is Changing Everything. [(accessed on 5 September 2020)];CISCO White Pap. 2011 1:1–11. Available online: https://www.cisco.com/c/dam/en_us/about/ac79/docs/innov/IoT_IBSG_0411FIN....
    1. CS Inc. Fog Computing and the Internet of Things: Extend the Cloud to Where the Things Are. [(accessed on 5 September 2020)];CISCO White Pap. 2016 1:1–6. Available online: https://www.cisco.com/c/dam/en_us/solutions/trends/iot/docs/computing-ov....
    1. Chang Z., Zhou Z., Ristaniemi T., Niu Z. Energy Efficient Optimization for Computation Offloading in Fog Computing System; Proceedings of the GLOBECOM 2017—2017 IEEE Global Communications Conference; Singapore. 4–8 December 2017; pp. 1–6.
    1. Liu L., Chang Z., Guo X., Mao S., Ristaniemi T. Multiobjective Optimization for Computation Offloading in Fog Computing. IEEE Internet Things J. 2018;5:283–294. doi: 10.1109/JIOT.2017.2780236. - DOI
    1. Hidano S., Murakami T., Katsumata S., Kiyomoto S., Hanaoka G. Model Inversion Attacks for Prediction Systems: Without Knowledge of Non-Sensitive Attributes; Proceedings of the 2017 15th Annual Conference on Privacy, Security and Trust (PST); Calgary, AB, Canada. 28–30 August 2017.

LinkOut - more resources

  NODES
INTERN 8
twitter 2