Differential Privacy Techniques for Cyber Physical Systems: A Survey
Open accessThe DOI matches its Crossref record; 361 of the 369 references it cites were found in a registry or an index.
Abstract
Modern cyber physical systems (CPSs) has widely being used in our daily lives because of development of information and communication technologies (ICT). With the provision of CPSs, the security and privacy threats associated to these systems are also increasing. Passive attacks are being used by intruders to get access to private information of CPSs. In order to make CPSs data more secure, certain privacy preservation strategies such as encryption, and k-anonymity have been presented in the past. However, with the advances in CPSs architecture, these techniques also need certain modifications. Meanwhile, differential privacy emerged as an efficient technique to protect CPSs data privacy. In this paper, we present a comprehensive survey of differential privacy techniques for CPSs. In particular, we survey the application and implementation of differential privacy in four major applications of CPSs named as energy systems, transportation systems, healthcare and medical systems, and industrial Internet of things (IIoT). Furthermore, we present open issues, challenges, and future research direction for differential privacy techniques for CPSs. This survey can serve as basis for the development of modern differential privacy techniques to address various problems and data privacy scenarios of CPSs.
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
“Besides broader survey studies, there are studies that focus on specific PPML techniques such as DP techniques for cyber-physical systems [48], privacy preservation in blockchain-based IoT systems [49], DP in deep-FL [28], and HE [109] and SMPC [184] for secure PPML computation.”
From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [48]
In the citing paper
“The privacy budget ( 𝜖 ) governs the trade-off between privacy and utility: smaller 𝜖 values strengthen privacy but degrade model accuracy [48, 191].”
From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [48]
In the citing paper
“For example, DP noise injection reduces privacy leakage but degrades model accuracy, necessitating adaptive budget allocation strategies tailored to non-IID settings.”
From Privacy-preserving Machine Learning in Internet of Vehicle Applications: Fundamentals, Recent Advances, and Future Direction (2025) · cites this paper as [48]
In the citing paper
“Hassan et al. [10] investigated the latest work on differential privacy techniques in consumer product security scenarios, reviewed previous research articles on differential privacy and highlighted the important features of these articles by focusing more on the practical aspects.”
From A Survey of IoT Privacy Security: Architecture, Technology, Challenges, and Trends (2024) · cites this paper as [10]
In the citing paper
“many malicious actors continue to develop a variety of adversarial attacks on sensitive data, posing ongoing threats to data security and privacy measures [51,74,76].”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [74]
Citations
Cites
k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
SWEENEY, L. (2002) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488502001648 · Cited by 8,571 · cited 1×
“such as k-anonymity [16] are also proposed by researchers to address privacy issues.”
BackgroundScheduling algorithms for multiprogramming in a hard-real-time environment
Liu, C. L., & Layland, J. W. (1973) · Journal of the ACM · doi:10.1145/321738.321743 · Cited by 8,433 · cited 1×
“From this motivation, in 1973, the first computer which was capable of real-time computations was developed [117], which addressed the problem of scheduling multiple tasks so that every job gets completed before the deadline.”
BackgroundBuyya, R., Yeo, C. S., Venugopal, S., Broberg, J., & Brandic, I. (2009) · Future Generation Computer Systems · doi:10.1016/j.future.2008.12.001 · Cited by 5,937
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557 · cited 2×
“They are named as Laplace mechanism (LM) [85], Gaussian mechanism [86], and Exponential mechanism (EM) [44].”
BackgroundDwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291 · cited 9×
“In 2006, C. Dwork proposed the concept of differential privacy as an efficient privacy preserving approach to obstruct adversaries from recovering data [24].”
BackgroundMethodInfluentialInternet of Things in industries: A survey
Xu, L. D., He, W., & Li, S. (2014) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2014.2300753 · Cited by 5,172 · cited 2×
“This term of Industrial Internet of Things (IIoT) flourished when researchers started integrating concepts of Internet of Things (IoT) with the environment of industrial control systems (ICS) [136].”
BackgroundA Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems
Lee, J., Bagheri, B., & Kao, H.-A. (2015) · Manufacturing Letters · doi:10.1016/j.mfglet.2014.12.001 · Cited by 5,113 · cited 1×
“1) System Architectures: Generally, CPSs architectures consists of two major functional components [123]: (i) Advanced Connectivity, in which the real-time data transmission and reception is taking part between physical world and cyber space; and (ii) Intelligent Data Management, in which computational, and analytical…”
BackgroundEvent-Triggered Real-Time Scheduling of Stabilizing Control Tasks
Tabuada, P. (2007) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2007.904277 · Cited by 4,702 · cited 1×
“The major issues NCSs face are: reduction of network traffic load due to sampling [125]–[127], network induced delays [128], packet dropout phenomenon [129], and quantization errors [130].”
BackgroundThe Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
A Survey of Recent Results in Networked Control Systems
Hespanha, J. P., Naghshtabrizi, P., & Xu, Y. (2007) · Proceedings of the IEEE · doi:10.1109/jproc.2006.887288 · Cited by 3,806 · cited 1×
“The major issues NCSs face are: reduction of network traffic load due to sampling [125]–[127], network induced delays [128], packet dropout phenomenon [129], and quantization errors [130].”
Background
Research works printed but not linked: 15
- pal, 0, On optimal privacy engineering for the smart micro-grid, IEEE Trans Knowl Data Eng
- apostol, 2012, Brute-Force Attacks
- thompson, 2007, Industrial Data Communications
- dankar, 2013, Practicing differential privacy in health care: A review, Trans Data Privacy, 6, 35
- zetter, 2015, A Cyberattack Has Caused Confirmed Physical Damage for the Second Time Ever
- bartoli, 2011, Security and privacy in your smart city, Proc of the Barcelona Smart Cities Congress, 292, 1
- 2016, Smart buildings enable smart cities [Online]
- kreutzmann, 2011, Protection profile for the gateway of a smart metering system, Federal Office for Information Security Germany
- jawurek, 2012, SoK Privacy Technologies for Smart Grids—A Survey of Options
- baumeister, 2010, Literature Review on Smart Grid Cyber Security
- lynch, 1995, Hybrid I/O automata, Proc Int Workshop Hybrid Syst, 496
- eckhoff, 2013, Privacy and surveillance: Concerns about a future transportation system, Proc 1st GI/ITG KuVS Fachgespräch Inter Veh Commun (FG IVC), 15
- tockar, 2014, Riding with the stars Passenger privacy in the NYC taxicab dataset
- eckert, 1946, Outline of Plans for Development of Electronic Computers
- bezzi, 2010, An information theoretic approach for privacy metrics, Trans Data Privacy, 3, 199
Cited by
Items 201–300 of 589
Privacy Preserving Federated Learning for Energy Disaggregation of Smart Homes
Ali, M., Kumar, A., & Choi, B. J. (2025) · IET Cyber-Physical Systems Theory & Applications · doi:10.1049/cps2.70013 · Cited by 15
Temporal Attention Source-Free Adaptation for Chemical Processes Fault Diagnosis
Xiao, Y., Shi, H., Song, B., Tao, Y., Tan, S., & Wang, B. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3312409 · Cited by 15
“While there have been several studies on privacy preserving in process industrial from the perspective of differential privacy [12], [13], they inevitably lead to a negative impact on the model accuracy and additional computational costs [14].”
BackgroundDabrowska, A. K., Kobus, M., Sowiński, P., Starzak, Ł., & Pękosławski, B. (2024) · Applied Sciences · doi:10.3390/app14020586 · Cited by 15
A Review on Security and Privacy Issues Pertaining to Cyber-Physical Systems in the Industry 5.0 Era
Alabdulatif, A., Thilakarathne, N. N., & Lawal, Z. K. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.054150 · Cited by 19
Kil, Y.-S., Lee, Y.-J., Jeon, S.-E., Oh, Y.-S., & Lee, I.-G. (2024) · IEEE Access · doi:10.1109/access.2024.3467049 · Cited by 17
“DP is a technology that adds artificial noise, which maintains a trade-off between privacy and accuracy and can protect data in real-time and prevent information leakage by adding a desired amount of noise [19].”
BackgroundPrivacy preservation techniques through data lifecycle: A comprehensive literature survey
Madhusudhanan, S., & Jose, A. C. (2025) · Computers & Security · doi:10.1016/j.cose.2025.104473 · Cited by 17
Welding flame detection based on color recognition and progressive probabilistic Hough transform
Chen, W., Chen, S., Guo, H., & Ni, X. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5815 · Cited by 15
Differential privacy protection method based on published trajectory cross-correlation constraint
Hu, Z., & Yang, J. (2020) · PLoS ONE · doi:10.1371/journal.pone.0237158 · Cited by 15
“The calculated noise value complies with the actual value of Laplace distribution, which is noise*Lap(Δf /ε) [19].”
BackgroundLu, H., Li, C., Chen, W., & Jiang, Z. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.10.016 · Cited by 15
PREEN: An Aggregation Mechanism for Privacy-Preserving Smart-Metering Communications
Wang, T., Jin, J., Gu, X., Zhang, Y., & Chen, X. (2022) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2022.3225088 · Cited by 15
Du, L., Cui, Z., Wang, L., & Ma, J. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5688 · Cited by 15
A differentially private greedy decision forest classification algorithm with high utility
Guan, Z., Sun, X., Shi, L., Wu, L., & Du, X. (2020) · Computers & Security · doi:10.1016/j.cose.2020.101930 · Cited by 15
Density peaks clustering based on k‐nearest neighbors sharing
Fan, T., Yao, Z., Han, L., Liu, B., & Lv, L. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5993 · Cited by 15
An efficient framework for data aggregation in smart agriculture
Yuan, J., Liu, W., Wang, J., Shi, J., & Miao, L. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6160 · Cited by 15
Differentially Private Dynamic Pricing for Efficient Demand Response in Smart Grid
Hassan, M. U., Rehmani, M. H., & Chen, J. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9149131 · Cited by 15
“Where R is the value of output, D is assigned dataset, and Q is the query function which satisfies ε -differential privacy [11].”
BackgroundSelf-citationEnhancing IoT privacy with artificial intelligence: Recent advances and future directions
Tsouplaki, A., Fung, C., & Kalloniatis, C. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101752 · Cited by 16
Hafeez, K., O’Shea, D., Newe, T., & Rehmani, M. H. (2023) · Scientific Reports · doi:10.1038/s41598-023-45725-9 · Cited by 14
“Over the past number of years, various contributions have been proposed allowing the benefits of DR, while ensuring privacy of the home occupant, such as Encryption, Battery based load hiding, and Differential Privacy, etc [5], [6].”
BackgroundSelf-citationIoT Privacy-Preserving Data Mining With Dynamic Incentive Mechanism
Gao, Y., Chen, L., Han, J., Wu, G., & Susilo, W. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3285894 · Cited by 14
“The noise scale of DP is sensitive to the privacy budget, which in turn increases data availability dramatically with the privacy budget [42], [43], [44].”
BackgroundData Utilization Versus Privacy Protection in Semantic Communications
Zhao, L., Wu, D., & Zhou, L. (2023) · IEEE Wireless Communications · doi:10.1109/mwc.007.2200503 · Cited by 15
“For instance, sharing data transparently faces a huge risk of privacy leakage, while the distributed learning frameworks based on differential privacy suffer from the data utility loss [8].”
BackgroundMethodMiglani, A., & Kumar, N. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3322826 · Cited by 14
“However, the usage of differential privacy may lead to a trade-off between accuracy and privacy as noise addition to data leads to loss of precision in data [34].”
BackgroundPower Profiling of Smart Grid Users Using Dynamic Time Warping
Kim, M., Firoozjaei, M. D., Kim, H., & El-Hajj, M. (2025) · Electronics · doi:10.3390/electronics14102015 · Cited by 14
Anonymization as homeomorphic data space transformation for privacy-preserving deep learning
Girka, A., Terziyan, V. Y., Gavriushenko, M., & Gontarenko, A. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.01.337 · Cited by 18
“Four major applications of differential privacy in cyber-physical systems (together with open issues and remaining problems) has been reported in [16], which are energy systems, transportation systems, healthcare and medical systems, and industrial internet of things.”
BackgroundPrivacy-Preserving Neural Networks for Smart Manufacturing
Lee, H., Finke, D. A., & Yang, H. Y. (2024) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4063728 · Cited by 17
Bi, R., Zhao, M., Ying, Z., Tian, Y., & Xiong, J. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2022.07.013 · Cited by 14
Privacy preservation in the internet of vehicles using local differential privacy and IOTA ledger
Iftikhar, Z., Anjum, A., Khan, A., Shah, M. A., & Jeon, G. (2023) · Cluster Computing · doi:10.1007/s10586-023-04002-0 · Cited by 13
“Anonymization solutions are not the best privacy preservation solutions because of two main reasons; (i) they are computationally expensive [18] and (ii) de-anonymization is possible through pseudonymization [19].”
Differential Privacy Configurations in the Real World: A Comparative Analysis
Khavkin, M., & Toch, E. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3603731 · Cited by 19
“Analyzing the way existing commercial, governmental and academic DP implementations are configured is crucial to understanding how organizations can set up DP as part of their operational process and the potential limitations and promises of their deployments.”
Differential Privacy for Second-Order Bipartite Consensus Over Signed Digraph
Tian, R., Zuo, Z., Han, Q., Wang, Y., & Zhang, W. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3370217 · Cited by 13
“Therefore, differential privacy captures massive interests from various fields [26], [27], [28], [29], [30].”
BackgroundPrivate outsourced model predictive control via secure multi-party computation
Adelipour, S., & Haeri, ء. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109208 · Cited by 13
Zhang, Y., Wang, Y., Chen, T., & Shi, J. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5707 · Cited by 13
A many‐objective integrated evolutionary algorithm for feature selection in anomaly detection
Zhang, Z., & Xie, L. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5861 · Cited by 13
Chen, T., Peng, L., Yang, J., & Cong, G. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6201 · Cited by 13
Personalized Privacy Preservation for Smart Grid
Bhattacharjee, A., Badsha, S., & Sengupta, S. (2021) · IEEE International Smart Cities Conference (ISC2) · doi:10.1109/isc253183.2021.9562929 · Cited by 15
Hand gesture recognition based on attentive feature fusion
Yu, B., Luo, Z., Wu, H., & Li, S. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5910 · Cited by 13
“S = Fgp(I) = 1 H × W H ∑ i=1 W ∑ j=1 I(i, j), (2)”
Wang, J., Jiang, Z., Li, F., & Chen, W. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6003 · Cited by 13
Differential Privacy for Deep Learning-based Online Energy Disaggregation System
Zhang, X., & Kuenzel, S. (2020) · IEEE PES Innovative Smart Grid Technologies Europe · doi:10.1109/isgt-europe47291.2020.9248901 · Cited by 13
“There are serval noise addition mechanisms available in the literature [13], including Laplace mechanism, Exponential mechanism, and Gaussian mechanism.”
MethodMedicine's New Rhythm: Harnessing Acoustic Sensing via the Internet of Audio Things for Healthcare
Pervez, F., Shoukat, M., Suresh, V., Farooq, M. U. B., Sandhu, M. M., Qayyum, A., Usama, M., Girardi, A. M., Latif, S., & Qadir, J. (2024) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2024.3462812 · Cited by 16
“To protect the sensitive attributes in the audio data, Hassan et al. [179] proposed the use of differential privacy techniques for IoAuT.”
MethodZhu, L., & Chen, X. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06845-9 · Cited by 14
“By strategically applying different types of DP at various stages of the data processing pipeline, this approach enhances the flexibility and efficiency of privacy protection, making it more adaptable to the specific demands of different applications [47, 48].”
Transforming Physiology and Healthcare through Foundation Models
Godwin, R. C., Tung, A., Berkowitz, D. E., & Melvin, R. L. (2025) · Physiology · doi:10.1152/physiol.00048.2024 · Cited by 13
Lian, Z., Yu, H., Chen, Y., Shahidehpour, M., & Zhou, Q. (2025) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2025.3594453 · Cited by 12
“Following the definition in [29], let M ( · ) denote a stochastic mapping from the private dataset The concept of (cid:6) -differential privacy for the private dataset is then introduced.”
Dynamic calibration of trust and trustworthiness in AI-enabled systems
Liebherr, M., Enkel, E., Law, E. L., Mousavi, M. R., Sammartino, M., & Sieberg, P. M. (2026) · International Journal on Software Tools for Technology Transfer · doi:10.1007/s10009-026-00840-6 · Cited by 17
“Examples of such trustworthy-by-construction techniques include privacy-preserving architectures for AI [1] and AI-enabled systems [134]; certified (adversarial) robustness for AI [13, 23]; and inherently explainable AI models [105].”
Differential privacy applied to smart meters: a mapping study
Marks, J. A., Montano, B., Chong, J., Raavi, M., Islam, R., Cerny, T., & Shin, D. (2021) · ACM Symposium on Applied Computing · doi:10.1145/3412841.3442360 · Cited by 17
“Even without smart meters, non-intrusive load monitoring (NILM) techniques can detect what appliances are being used in a home [1, 3].”
BackgroundMethodInfluentialSubstation instrumentation target detection based on multi‐scale feature fusion
Feng, Q., Huang, L., Sun, Y., Tong, X., Liu, X., Xie, Y., Li, J., Fan, H., & Chen, B. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7177 · Cited by 12
Neighborhood rough set based multi‐label feature selection with label correlation
Wu, Y., Liu, J., Yu, X., Lin, Y., & Li, S. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7162 · Cited by 12
“(4) Furthermore, the average classification performance of NRS-LC surpasses all comparing algorithms on different evaluation metrics.”
MethodAI and Blockchain for Cybersecurity in Cyber-Physical Systems: Challenges and Future Research Agenda
Girdhar, K., Singh, C., & Kumar, Y. (2023) · Advances in information security · doi:10.1007/978-3-031-25506-9_10 · Cited by 13
Adversarial false data injection attacks on deep learning‐based short‐term wind speed forecasting
Yang, L., Liang, G., Yang, Y., Ruan, J., Yu, P., & Yang, C. R. (2023) · IET Renewable Power Generation · doi:10.1049/rpg2.12853 · Cited by 12
LDP-Feat: Image Features with Local Differential Privacy
Pittaluga, F., & Zhuang, B. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01612 · Cited by 21
“Most differential privacy research is focused on the centralized setting [17], where raw user data is aggregated by a trusted curator who then shares the data to the public without releasing private information.”
BackgroundA cluster-based appliance-level-of-use demand response program design
Wu, J., Lu, C., Wu, C., Shi, J. F., González, M. C., Wang, D., & Han, Z. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.123003 · Cited by 12
Ren, X., Yu, C.-M., Yu, W., Yang, X., Zhao, J., & Yang, S. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3020089 · Cited by 12
“Differential privacy (DP), as the de-facto paradigm for privacy preservation with rigorous guarantee [18], [19], has received considerable attention in the privacy protection of monitoring or crowdsourced data, focusing on either data publication [20]–[23] or statistical aggregation [9], [10], [24], [25].”
BackgroundYang, Q., Yin, S., Li, Q., & Li, Y. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7126 · Cited by 12
Edge-computing enhanced privacy protection for industrial ecosystems in the context of SMEs
Giehl, A., Schneider, P., Busch, M., Schnoes, F., Kleinwort, R., & Zaeh, M. F. (2019) · doi:10.1109/cmi48017.2019.8962138 · Cited by 13
“For enhancing the control over the data before releasing them to the cloud data centers, sophisticated privacy models are available for industrial settings [6].”
BackgroundMethodManzoor, H. U., Arshad, K., Assaleh, K. T., & Zoha, A. (2024) · doi:10.36227/techrxiv.171468119.91309905/v1 · Cited by 14
Security Analysis and Defense of Multi-Encoding Mechanism Against Eavesdropping Attacks
Wang, J., Yang, W. D., Chen, G., Zhou, J., & Ding, W. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3565302 · Cited by 11
“To be specific, distortion algorithm protects the privacy of sensitive data by adding noise into the sensitive data, which is at the expense of some sys-tem performance, such as differential privacy [31], [32].”
Performance evaluation of differential privacy mechanisms in blockchain-based smart metering
Hassan, M. U., Rehmani, M. H., & Chen, J. (2020) · Institution of Engineering and Technology eBooks · doi:10.1049/pbpc029e_ch9 · Cited by 12
Self-citationZhang, Y., Zhao, J., Qiang, Y., Yang, X., Wu, W., & Jia, L. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6535 · Cited by 12
“We compare proposed method with several most advanced unsupervised feature selection method: (1) LapScore,56 (2) PCASCore, (3) LuFS,57 (4) UFSACO,58 (5) ours.”
MethodOnline streaming feature selection for multigranularity hierarchical classification learning
Wang, C., Zhang, X., Ye, L., Mao, Y. X., Li, S., & Lin, Y. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6994 · Cited by 11
Liu, D., Wu, Y., Hong, D., & Wang, S. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7331 · Cited by 14
Evaluating the Privacy and Utility of Time-Series Data Perturbation Algorithms
Roman, A.-S. (2023) · Mathematics · doi:10.3390/math11051260 · Cited by 13
“However, obtaining the desired trade-off between privacy and accuracy may be challenging for time series, and it may reduce data utility [15,26].”
BackgroundMethodCompound lower limb vibration training rehabilitation robot
Yin, Q., Hu, A., Li, Q., Wei, X., Yang, H., Wang, B., & Zhang, G. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6059 · Cited by 11
A threshold group signature scheme suitable for the Internet of Things
Gong, B., Zhang, X., Cao, Y., Li, Z., Yang, J., & Wang, W. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6243 · Cited by 11
Fan, T., & Cui, Z. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6367 · Cited by 11
Li, K., Fu, X., Wang, F., & Jalil, H. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6773 · Cited by 11
“Before the mutation operation of each generation, for each individual Xi, an integer ri is randomly selected from Reference 1, [i], and the MCR,ri,MF,ri value pairs corresponding to the index ri are retrieved from the historical memory MCR and MF, and Apply them to formula (9) and (10) to generate CRi and Fi correspon…”
BackgroundMethodA Control-Recoverable Added-Noise-Based Privacy Scheme for LQ Control in Networked Control Systems
Tang, X., Cao, X., & Zheng, W. X. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3495373 · Cited by 10
“Regarding privacy-preserving of x ( k ) by the AN, the criterion often used in literature is DP [18], [24].”
Disentangling classification and regression in Siamese‐based network for visual tracking
Zhang, X., Li, L., Liu, H., Yang, P., & Gao, Y. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7246 · Cited by 10
Object pose estimation based on stereo vision with improved K‐D tree ICP algorithm
Huang, L., Wang, C., Yun, J., Tao, B., Qi, J., Liu, Y., Ma, H., & Yu, H. L. (2023) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7714 · Cited by 10
The Future of Privacy: A Review on AI's Role in Shaping Data Security
Vardalachakis, M., Tampouratzis, M. G., Papadakis, N., & Vasilakis, M. (2024) · International Conference in Electronic Engineering & Information Technology (EEITE) · doi:10.1109/eeite61750.2024.10654397 · Cited by 12
“Differential privacy [29] ensures the confidentiality of patients throughout cooperation investigation efforts by enabling the exchange of private health information while revealing sensitive data.”
BackgroundLarge Language Models for Electronic Health Record De-Identification in English and German
Sousa, S., Jantscher, M., Kröll, M., & Kern, R. (2025) · Information · doi:10.3390/info16020112 · Cited by 12
Benchmarking Relaxed Differential Privacy in Private Learning: A Comparative Survey
Zheng, Z., Yao, L., Hu, H., & Wu, G. (2025) · ACM Computing Surveys · doi:10.1145/3729216 · Cited by 12
“DP satisfies two composition theorems to measure the degree of combined mechanisms like Laplace mechanism and Exponential mechanism [38].”
Heterogeneous Information Network-Based Scientific Workflow Recommendation for Complex Applications
Wen, Y., Hou, J., Yuan, Z., & Zhou, D. M. (2020) · Complexity · doi:10.1155/2020/4129063 · Cited by 10
Composite firefly algorithm for breast cancer recognition
Peng, H., Zhu, W., Deng, C., Yu, K., & Wu, Z. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6032 · Cited by 10
Manipulator trajectory tracking based on adaptive fuzzy sliding mode control
Zhao, H., Tao, B., Ma, R., & Chen, B. (2023) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7620 · Cited by 10
Neural Network Based Data Encryption: A Comparison Study among DES, AES, and HE Techniques
Yeow, S.-Q., & Ng, K.-W. (2023) · JOIV International Journal on Informatics Visualization · doi:10.30630/joiv.7.3-2.2336 · Cited by 11
Market Value of Differentially-Private Smart Meter Data
Chhachhi, S., & Teng, F. (2021) · IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT) · doi:10.1109/isgt49243.2021.9372228 · Cited by 10
“Although encryption, data aggregation and anonymization provide some increased privacy protection they do not guarantee that an individual cannot be identified or prevent user information leakage [4], [6].”
BackgroundFederated Constrastive Learning and Visual Transformers for Personal Recommendation
Belhadi, A., Djenouri, Y., Andrade, F. A. A., & Srivastava, G. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10286-0 · Cited by 11
Systematic Literature Review on Differential Privacy in Machine Learning
Jahan, S., Ge, Y.-F., Bertino, E., Kabir, E., Mahmud, H., Zheng, Z., & Wang, H. (2026) · ACM Computing Surveys · doi:10.1145/3800684 · Cited by 13
“A scoring function is used Simple and efficient Not suitable for high-dimensional data Exponential [28] Exponential 𝜖 -DP Non-numeric queries [54] Useful for categorical data Requires well-defined utility function Gaussian [28] Normal (0,𝜎 2 ) (𝜖,𝛿) -DP High-dimensional queries Flexible and…”
Kernel local outlier factor‐based fuzzy support vector machine for imbalanced classification
Wang, K., An, J., Yu, Z., Yin, X., & Ma, C. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6235 · Cited by 9
PriSIEM: Enabling privacy-preserving Managed Security Services
Coppolino, L., D’Antonio, S., Mazzeo, G., Romano, L., & Sgaglione, L. (2022) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2022.103397 · Cited by 10
Huang, H., Zhao, Y., Tang, X., Xiao, F., & Li, Q. L. (2022) · Information Sciences · doi:10.1016/j.ins.2022.09.052 · Cited by 9
Optimization-based pseudo random key generation for fast encryption scheme
Shawkat, S. A., Tagougui, N., & Kherallah, M. (2022) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v12i2.4953 · Cited by 9
DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning
Zhao, C., Ze, Y., Dong, J., Wang, B., & Li, S. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/516 · Cited by 9
“However, owners of autonomous vehicles may not allow their vehicles to send private information to other vehicles without any desensitization since this may divulge their private information such as their personal life routines [Hassan et al., 2020].”
BackgroundMulti-User Behavioral Privacy Filtering for mmWave Radar Sensing
Liu, X., Liu, H., Zhang, J., Xie, X. N., & Li, K. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3556674 · Cited by 9
“This approach shares a similar principle with differential privacy [14], [15] by protecting user privacy by adding noise to the data, where the amount of noise is crucial as it must effectively protect user privacy without causing the data to become unusable due to excessive noise.”
A Taxonomy of AI Techniques for Security and Privacy in Cyber–Physical Systems
Bandi, A. (2024) · Journal of Computational and Cognitive Engineering · doi:10.47852/bonviewjcce42021539 · Cited by 13
Joint multilabel classification and feature selection based on deep canonical correlation analysis
Dai, L., Du, G., Zhang, J., Li, C., Wei, R., & Li, S. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5864 · Cited by 9
“34,35,49 Inotherwords,Iftwo labels have strongly positive correlation, the predictions of one label may be close to the other one, and vise versa.”
BackgroundGrammar guided embedding based Chinese long text sentiment classification
Zhang, C., Lin, D., Cao, D., & Li, S. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6439 · Cited by 9
Anthi, E., Williams, L., Afzal, H. A., Brar, B. A., Bhowmick, J., Gujral, K., & Thomas, E. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3609972 · Cited by 15
You, M., Ge, Y.-F., Yin, J., Wang, K., Zheng, Z., Zhang, Y., & Wang, H. (2025) · ACM Transactions on the Web · doi:10.1145/3779413 · Cited by 8
“Static one-shot algorithms are vulnerable when data evolves: naive re-runs enable differencing/temporal inference across releases [2, 3, 17, 36].”
Robots as AI Double Agents: Privacy in Motion Planning
Shome, R., Kingston, Z. K., & Kavraki, L. E. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341460 · Cited by 11
Xia, L., Fan, J., Parlikad, A. K., Huang, X. X., & Zheng, P. (2024) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2024.3522814 · Cited by 13
“Nonetheless,collabo-rationamongdisparateclientspresentsacomplexundertaking, necessitatingacomprehensiveassessmentoftheadvantagesand potentialhazards,especiallyconcerningtheprotectionofdata privacy[13].”
Reddi, S., Rao, P. M., Saraswathi, P. V., Bera, B., Das, A. K., & Sikdar, B. (2025) · IEEE Communications Magazine · doi:10.1109/mcom.003.2400277 · Cited by 8
“Various approaches have been proposed, such as Attribute-Based Encryption (ABE) [2], adversarial ML-based cloud architecture [3], differential privacy techniques [1], and so on.”
Research on children's cognitive development for learning disabilities using recommendation method
Shen, X., & Xu, C. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6097 · Cited by 8
Wei, Z., & Nie, J. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6273 · Cited by 8
An identity privacy scheme for blockchain‐based on edge computing
Mu, R., Gong, B., Ning, Z., Zhang, J., Cao, Y., Li, Z., Wang, W., & Wang, X. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6545 · Cited by 8
Dynamic Risk Assessment and Certification in the Power Grid: A Collaborative Approach
Liatifis, A., Alcazar, P. R., Grammatikis, P. I. R., Papamartzivanos, D., Menesidou, S. A., Krousarlis, T., Molinuevo, A., Angulo, I., Sarigiannidis, A. G., Λάγκας, Θ., et al. (2022) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft54395.2022.9844034 · Cited by 8
“In [15] A. Risk Assessment in the Power Grid R. Habash et al. in [16] developed a risk assessment framework targeted towards Smart Grid (SG) environments.”
May the privacy be with us: Correlated differential privacy in location data for ITS
Chong, K. M., & Malip, A. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110214 · Cited by 8
Zhang, X., Liu, J., Cao, B., & Shi, M. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6202 · Cited by 8
Dynamic Network-Assisted D2D-Aided Coded Distributed Learning
Zeulin, N., Galinina, O., Himayat, N., Andreev, S. D., & Heath, R. W. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3259442 · Cited by 8
“To achieve the required privacy level, one may additionally apply sequential composition [25] of differentially-private mechanisms, such as adding Laplace or Gaussian noise.”
MethodHu, B., Xiao, H., Yang, N., Jin, H., & Wang, L. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6818 · Cited by 8
Malware detection method based on image analysis and generative adversarial networks
Liu, Y., Li, J., Liu, B., Gao, X., & Liu, X. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7170 · Cited by 8
Jiang, D., Jin, D., Zhuang, J., Tan, D., Chen, D., & Liang, Y. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6269 · Cited by 8
Causality‐based online streaming feature selection
Li, L., Lin, Y., Zhao, H., Chen, J., & Li, S. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6347 · Cited by 7
Self-citationResearch on four‐wheel independent steering intelligent control strategy based on minimum load
Chen, H., Chen, S., Zhou, R., Huang, X., & Zhu, S. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6145 · Cited by 7
“Equation (23) is the four-wheel steering angle expression in the OABML algorithm.”
Background
Metadata
- Authors
- Hassan, M. U., Rehmani, M. H., & Chen, J.
- Affiliations
- Swinburne University of Technology (AU)
- Munster Technological University (IE)
- Venue
- IEEE Communications Surveys & Tutorials
- Published
- 2020
- Volume
- 22
- Issue
- 1
- Pages
- 746-789
- ISSN
- 1553-877X (ISSN-L)
- 2373-745X
- OpenAlex
- W2978348882
- Cited by
- 564
- References
- 369
- Citations by year
- 2026: 39 · 2025: 68 · 2024: 74 · 2023: 89 · 2022: 88 · 2021: 121 · 2020: 78
- FWCI
- 33.53
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Communications Surveys & Tutorials (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Swinburne figshare (Swinburne University of Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Australian Research Council (DP190101893, DP170100136, LP140100816, LP180100758)
- 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, cyber-physical systems, data privacy, privacy preservation, energy systems, transport systems, healthcare data privacy, Industrial Internet of Things, k-anonymity, encryption, passive attacks
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.