Differential Privacy Preserving of Training Model in Wireless Big Data with Edge Computing
The DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
Abstract
With the popularity of smart devices and the widespread use of machine learning methods, smart edges have become the mainstream of dealing with wireless big data. When smart edges use machine learning models to analyze wireless big data, nevertheless, some models may unintentionally store a small portion of the training data with sensitive records. Thus, intruders can expose sensitive information by careful analysis of this model. To solve this privacy issue, in this paper, we propose and implement a machine learning strategy for smart edges using differential privacy. We focus our attention on privacy protection in training datasets in wireless big data scenario. Moreover, we guarantee privacy protection by adding Laplace mechanisms, and design two different algorithms Output Perturbation (OPP) and Objective Perturbation (OJP), which satisfy differential privacy. In addition, we consider the privacy preserving issues presented in the existing literatures for differential privacy in the correlated datasets, and further provided differential privacy preserving methods for correlated datasets, guaranteeing privacy by theoretical deduction. Finally, we implement the experiments on the TensorFlow, and evaluate our strategy on four datasets, i.e., MNIST, SVHN, CIFAR-10 and STL-10. The experiment results show that our methods can efficiently protect the privacy of training datasets and guarantee the accuracy on benchmark datasets.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Hence, Laplace noises [197] are added to these possibly exposed training data for enhancing the training data privacy assurance.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [196]
Citations
Cites
Calibrating Noise to Sensitivity in Private Data Analysis
Dwork, C., McSherry, F., Nissim, K., & Smith, A. (2006) · Lecture Notes in Computer Science · doi:10.1007/11681878_14 · Cited by 7,272
Deep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578
Fog computing and its role in the internet of things
Bonomi, F., Milito, R., Zhu, J., & Addepalli, S. (2012) · Proceedings of the first edition of the MCC workshop on Mobile cloud computing · doi:10.1145/2342509.2342513 · Cited by 6,244
Dwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, M., Jha, S., & Ristenpart, T. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813677 · Cited by 2,961
Best practices for convolutional neural networks applied to visual document analysis
Simard, P. Y., Steinkraus, D., & Platt, J. C. (2005) · Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings. · doi:10.1109/icdar.2003.1227801 · Cited by 2,741
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 3×
“Many works have been done on adding differential privacy for shallow machine learning models [25], [26], [36], [37], [59].”
BackgroundResultLiving on the edge: The role of proactive caching in 5G wireless networks
Bastug, E., Bennis, M., & Debbah, M. (2014) · IEEE Communications Magazine · doi:10.1109/mcom.2014.6871674 · Cited by 1,146
Kang, J., Yu, R., Huang, X., Maharjan, S., Zhang, Y., & Hossain, E. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2709784 · Cited by 1,139
Self-citationSmooth sensitivity and sampling in private data analysis
Nissim, K., Raskhodnikova, S., & Smith, A. (2007) · Proceedings of the thirty-ninth annual ACM symposium on Theory of computing · doi:10.1145/1250790.1250803 · Cited by 974
Boosting and Differential Privacy
Dwork, C., Rothblum, G. N., & Vadhan, S. (2010) · 2010 IEEE 51st Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2010.12 · Cited by 784 · cited 2×
“Both the loss function and the regularization are deriv-able and strongly convex [30].”
BackgroundFundamental challenges in mobile computing
Satyanarayanan, M. (1996) · Proceedings of the fifteenth annual ACM symposium on Principles of distributed computing - PODC '96 · doi:10.1145/248052.248053 · Cited by 666
Differentially private recommender systems: Building privacy into the Netflix Prize contenders
McSherry, F., & Mironov, I. (2009) · Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1557019.1557090 · Cited by 664
Kifer, D., & Machanavajjhala, A. (2011) · Proceedings of the 2011 ACM SIGMOD International Conference on Management of data · doi:10.1145/1989323.1989345 · Cited by 619
A survey on mobile edge computing
Ahmed, A., & Ahmed, E. (2016) · 2016 10th International Conference on Intelligent Systems and Control (ISCO) · doi:10.1109/isco.2016.7727082 · Cited by 598
Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds
Bun, M., & Steinke, T. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-662-53641-4_24 · Cited by 584
Boosting the accuracy of differentially private histograms through consistency
Hay, M., Rastogi, V., Miklau, G., & Suciu, D. (2010) · Proceedings of the VLDB Endowment · doi:10.14778/1920841.1920970 · Cited by 528
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
Papernot, N., Abadi, M., Erlingsson, Ú., Goodfellow, I., & Talwar, K. (2016) · arXiv · doi:10.48550/arxiv.1610.05755 · Cited by 492
Caching at the wireless edge: design aspects, challenges, and future directions
Liu, D., Chen, B., Yang, C., & Molisch, A. F. (2016) · IEEE Communications Magazine · doi:10.1109/mcom.2016.7565183 · Cited by 457
NFV: state of the art, challenges, and implementation in next generation mobile networks (vEPC)
Hawilo, H., Shami, A., Mirahmadi, M., & Asal, R. (2014) · IEEE Network · doi:10.1109/mnet.2014.6963800 · Cited by 456
Home M2M networks: Architectures, standards, and QoS improvement
Zhang, Y., Yu, R., Xie, S., Yao, W., Xiao, Y., & Guizani, M. (2011) · IEEE Communications Magazine · doi:10.1109/mcom.2011.5741145 · Cited by 431
Self-citationCognitive machine-to-machine communications: visions and potentials for the smart grid
Zhang, Y., Yu, R., Nekovee, M., Liu, Y., Xie, S., & Gjessing, S. (2012) · IEEE Network · doi:10.1109/mnet.2012.6201210 · Cited by 386
Self-citationClustering of Electricity Consumption Behavior Dynamics Toward Big Data Applications
Wang, Y., Chen, Q., Kang, C., & Xia, Q. (2016) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2016.2548565 · Cited by 342
Dwork, C. (2011) · Encyclopedia of Cryptography and Security · doi:10.1007/978-1-4419-5906-5_752 · Cited by 339
Mobile big data analytics using deep learning and apache spark
Alsheikh, M. A., Niyato, D., Lin, S., Tan, H.-P., & Han, Z. (2016) · IEEE Network · doi:10.1109/mnet.2016.7474340 · Cited by 272
Correlated network data publication via differential privacy
Chen, R., Fung, B. C. M., Yu, P. S., & Desai, B. C. (2014) · The VLDB Journal · doi:10.1007/s00778-013-0344-8 · Cited by 215
Strategic Honeypot Game Model for Distributed Denial of Service Attacks in the Smart Grid
Wang, K., Du, M., Maharjan, S., & Sun, Y. (2017) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2017.2670144 · Cited by 214
Self-citationGreen Resource Allocation Based on Deep Reinforcement Learning in Content-Centric IoT
He, X., Wang, K., Huang, H., Miyazaki, T., Wang, Y., & Guo, S. (2020) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2018.2805718 · Cited by 208
Self-citationDynamic Differential Privacy for ADMM-Based Distributed Classification Learning
Zhang, T., & Zhu, Q. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2016.2607691 · Cited by 202
On sampling, anonymization, and differential privacy or, k -anonymization meets differential privacy
Li, N., Qardaji, W., & Su, D. (2012) · Proceedings of the 7th ACM Symposium on Information, Computer and Communications Security · doi:10.1145/2414456.2414474 · Cited by 202
Correlated Differential Privacy: Hiding Information in Non-IID Data Set
Zhu, T., Xiong, P., Li, G., & Zhou, W. (2015) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2014.2368363 · Cited by 174
Quantifying the Impact of Edge Computing on Mobile Applications
Hu, W., Gao, Y., Ha, K., Wang, J., Amos, B., Chen, Z., Pillai, P., & Satyanarayanan, M. (2016) · Proceedings of the 7th ACM SIGOPS Asia-Pacific Workshop on Systems · doi:10.1145/2967360.2967369 · Cited by 171
Exploring Mobile Edge Computing for 5G-Enabled Software Defined Vehicular Networks
Huang, X., Yu, R., Kang, J., He, Y., & Zhang, Y. (2017) · IEEE Wireless Communications · doi:10.1109/mwc.2017.1600387 · Cited by 169
Self-citationWireless Big Data Computing in Smart Grid
Wang, K., Wang, Y., Hu, X., Sun, Y., Deng, D.-J., Vinel, A., & Zhang, Y. (2017) · IEEE Wireless Communications · doi:10.1109/mwc.2017.1600256wc · Cited by 169
Self-citationBig Data Analytics for System Stability Evaluation Strategy in the Energy Internet
Wang, K., Li, H., Feng, Y., & Tian, G. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2692775 · Cited by 148
Self-citationCost-friendly Differential Privacy for Smart Meters: Exploiting the Dual Roles of the Noise
Zhang, Z., Qin, Z., ZHU, L., Weng, J., & Ren, K. (2016) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2016.2585963 · Cited by 141
Mobile big data fault-tolerant processing for ehealth networks
Wang, K., Shao, Y., Shu, L., Zhu, C., & Zhang, Y. (2016) · IEEE Network · doi:10.1109/mnet.2016.7389829 · Cited by 136
Self-citationFundamental Challenges in Mobile Computing,
Satyanarayanan, M. (1996) · Defense Technical Information Center (DTIC) · doi:10.21236/ada306271 · Cited by 132
Differentially private publication of general time-serial trajectory data
Hua, J., Gao, Y., & Zhong, S. (2015) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2015.7218422 · Cited by 114
Beyond worst-case analysis in private singular vector computation
Hardt, M., & Roth, A. (2013) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/2488608.2488650 · Cited by 95
Ding, X., Tian, Y., & Yu, Y. P. (2015) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2015.2436337 · Cited by 92
Optimal Noise Adding Mechanisms for Approximate Differential Privacy
Geng, Q., & Viswanath, P. (2016) · IEEE Transactions on Information Theory · doi:10.1109/tit.2015.2504972 · Cited by 91
Components of fog computing in an industrial internet of things context
Gazis, V., Leonardi, A., Mathioudakis, K., Sasloglou, K., Kikiras, P., & Sudhaakar, R. (2015) · 2015 12th Annual IEEE International Conference on Sensing, Communication, and Networking - Workshops (SECON Workshops) · doi:10.1109/seconw.2015.7328144 · Cited by 90
Game-Theory-Based Active Defense for Intrusion Detection in Cyber-Physical Embedded Systems
Wang, K., Du, M., Yang, D., Zhu, C., Shen, J., & Zhang, Y. (2016) · ACM Transactions on Embedded Computing Systems · doi:10.1145/2886100 · Cited by 82
Self-citationSecure Two-Party Differentially Private Data Release for Vertically Partitioned Data
Mohammed, N., Alhadidi, D., Fung, B. C. M., & Debbabi, M. (2013) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2013.22 · Cited by 81
LDPA: a local data processing architecture in ambient assisted living communications
Wang, K., Shao, Y. F., Shu, L., et al. (2015) · IEEE Communications Magazine · doi:10.1109/mcom.2015.7010516 · Cited by 77
Self-citationCollaborative Search Log Sanitization: Toward Differential Privacy and Boosted Utility
Hong, Y., Vaidya, J. S., Lu, H., Karras, P., & Goel, S. (2014) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2014.2369034 · Cited by 74
A Differential Privacy-Based Query Model for Sustainable Fog Data Centers
Du, M., Wang, K., Liu, X., Guo, S., & Zhang, Y. (2017) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2017.2715038 · Cited by 68
Self-citationEmbracing big data with compressive sensing: a green approach in industrial wireless networks
Kong, L., Zhang, D., He, Z., Xiang, Q., Wan, J., & Tao, M. (2016) · IEEE Communications Magazine · doi:10.1109/mcom.2016.7588229 · Cited by 65
Attack Detection and Distributed Forensics in Machine-to-Machine Networks
Wang, K., Du, M., Sun, Y., Vinel, A., & Zhang, Y. (2016) · IEEE Network · doi:10.1109/mnet.2016.1600113nm · Cited by 63
Self-citationDifferential privacy for the analyst via private equilibrium computation
Hsu, J., Roth, A., & Ullman, J. (2013) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/2488608.2488651 · Cited by 43
Secure Distributed Framework for Achieving ε-Differential Privacy
Alhadidi, D., Mohammed, N., Fung, B. C. M., & Debbabi, M. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31680-7_7 · Cited by 41
A Pre-Authentication Approach to Proxy Re-Encryption in Big Data Context
Wang, K., Yu, J., Liu, X., et al. (2017) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2017.2702176 · Cited by 40
Self-citationTowards Differential Query Services in Cost-Efficient Clouds
Liu, Q., Tan, C. C., Wu, J., et al. (2013) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2013.132 · Cited by 31
Exploiting LTE D2D communications in M2M Fog platforms: Deployment and practical issues
Vallati, C., Virdis, A., Mingozzi, E., & Stea, G. (2015) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot.2015.7389119 · Cited by 30
Differential Forms for Target Tracking and Aggregate Queries in Distributed Networks
Sarkar, R., & Gao, J. (2012) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2012.2220857 · Cited by 30
Computing on Base Station Behavior Using Erlang Measurement and Call Detail Record
Zhang, S., Yin, D., Zhang, Y., & Zhou, W. (2015) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2015.2389614 · Cited by 28
Self-citationA Selective Privacy-Preserving Approach for Multimedia Data
Li, H., Wang, K., Liu, X., Sun, Y., & Guo, S. (2017) · IEEE Multimedia · doi:10.1109/mmul.2017.4031322 · Cited by 28
Self-citationEfficient Trustworthiness Management for Malicious User Detection in Big Data Collection
Yu, J., Wang, K., Li, P., Xia, R., Guo, S., & Guo, M. (2017) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2017.2761386 · Cited by 24
Self-citationm-Privacy for Collaborative Data Publishing
Goryczka, S., Xiong, L., & Fung, B. C. M. (2011) · International Conference on Collaborative Computing: Networking, Applications and Worksharing (CollaborateCom) · doi:10.4108/icst.collaboratecom.2011.247094 · Cited by 22
Analyzing Big Smart Metering Data Towards Differentiated User Services: A Sublinear Approach
Pan, E., Wang, D., & Han, Z. (2016) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2016.2599924 · Cited by 19
A Semi-Supervised Learning Approach to Differential Privacy
Jagannathan, G., Monteleoni, C., & Pillaipakkamnatt, K. (2013) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2013.131 · Cited by 18
Pseudonym exchange for privacy-preserving publishing of trajectory data set
Mano, K., Minami, K., & Maruyama, H. (2014) · IEEE Global Conference on Consumer Electronics (GCCE) · doi:10.1109/gcce.2014.7031175 · Cited by 7
Research works printed but not linked: 4
- 10.1109/FOCS.2010.12 · DOI · Paper page
- dwork, 2006, Scalibrating noise to sensitivity in private data analysis, Proc Theory Cryptography Conf, 265
- 2015, Fog computing and the Internet of Things: Extend the cloud to where the things are, White Paper Cisco San Jose CA USA
- 2014, Iox Overview, Cisco San Jose CA USA
Cited by
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498
“Different from [190]–[192], in the scenario of [196], training”
BackgroundKhan, W. Z., Ahmed, E., Hakak, S., Yaqoob, I., & Ahmed, A. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.02.050 · Cited by 1,157
Pham, Q.-V., Fang, F., Ha, V. N., Piran, M. J., Le, M., Le, L. B., Hwang, W.-J., & Ding, Z. (2020) · IEEE Access · doi:10.1109/access.2020.3001277 · Cited by 870
Building an efficient intrusion detection system based on feature selection and ensemble classifier
Zhou, Y., Cheng, G., Jiang, S., & Dai, M. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107247 · Cited by 675
Differential Privacy Techniques for Cyber Physical Systems: A Survey
Hassan, M. U., Rehmani, M. H., & Chen, J. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2944748 · Cited by 564
Metadata
- Authors
- Du, M., Wang, K., Xia, Z., & Zhang, Y.
- Affiliations
- Nanjing University of Posts and Telecommunications (CN)
- Hong Kong Polytechnic University (HK)
- Changsha University of Science and Technology (CN)
- University of Oslo (NO)
- Venue
- IEEE Transactions on Big Data
- Published
- 2020-06-01
- Volume
- 6
- Issue
- 2
- Pages
- 283-295
- ISSN
- 2332-7790 (ISSN-L)
- 2372-2096
- OpenAlex
- W2800696118
- Cited by
- 111
- References
- 63
- Citations by year
- 2026: 3 · 2025: 9 · 2024: 10 · 2023: 10 · 2022: 24 · 2021: 17 · 2020: 24
- FWCI
- 7.75
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Big Data (publishedVersion)
- Funders
- National Natural Science Foundation of China (61572262)
- China Postdoctoral Science Foundation (2017M610252, 2017T100297)
- Norges Forskningsråd (240079/F20)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
- Keywords
- differential privacy, training data privacy, edge computing, Laplace mechanism, output perturbation, privacy-preserving machine learning
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.