More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence
Open accessThe DOI matches its Crossref record; 151 of the 152 references it cites were found in a registry or an index.
Abstract
Artificial Intelligence (AI) has attracted a great deal of attention in recent years. However, alongside all its advancements, problems have also emerged, such as privacy violations, security issues and model fairness. Differential privacy, as a promising mathematical model, has several attractive properties that can help solve these problems, making it quite a valuable tool. For this reason, differential privacy has been broadly applied in AI but to date, no study has documented which differential privacy mechanisms can or have been leveraged to overcome its issues or the properties that make this possible. In this paper, we show that differential privacy can do more than just preserve privacy. It can also be used to improve security, stabilize learning, build fair models, and impose composition in selected areas of AI. With a focus on regular machine learning, distributed machine learning, deep learning, and multi-agent systems, the purpose of this article is to deliver a new view on many possibilities for improving AI performance with differential privacy techniques.
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The data that is collected or used by third parties, without the authorization or voluntary consent of individuals, would result in the violations of their privacy (Wu et al., 2022;Zhu et al., 2020).”
From Artificial intelligence governance: Ethical considerations and implications for social responsibility (2024) · cites this paper as Zhu et al., 2020
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Differential privacy [17, 18] guarantees that by looking at a model output, one cannot tell whether a sample is in the training dataset or not.”
From Machine Unlearning: A Survey (2024) · cites this paper as [17]
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512
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
Intelligent agents: theory and practice
Wooldridge, M., & Jennings, N. R. (1995) · The Knowledge Engineering Review · doi:10.1017/s0269888900008122 · Cited by 6,810 · cited 1×
“domain problems [99], [100].”
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
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322 · cited 1×
“Federated learning was first proposed by Google in 2017 as an additional approach to the standard centralised machine learning approaches [78], and has been applied to several real-world applications [79].”
BackgroundA Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
Dwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291
Research works printed but not linked: 12
- Russell, 2002, Artificial Intelligence: A Modern Approach
- 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
- Chaudhuri, 2011, Differentially private empirical risk minimization, J. Mach. Learn. Res., 12, 1069
- Nobel, 2018, Algorithms of Oppression: How Search Engines Reinforce Racism, 10.18574/nyu/9781479833641.001.0001 · DOI · Paper page
- Zemel, Learning fair representation, III-325
- Dwork, Fairness under composition, 33:1
- Zhao, Distributed deep learning under differential privacy with the teacher-student paradigm, 404
- 10.1145/3298981 · DOI · Paper page
- Bhagoji, Analyzing federated learning through an adversarial lens, 634
- 10.1145/2660267.2660348 · DOI · Paper page
- Bonanno, 2018, Game Theory
- 10.1145/2976734 · DOI
Cited by
Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning
Fang, H., & Qian, Q. (2021) · Future Internet · doi:10.3390/fi13040094 · Cited by 424
“Besides that, differential privacy is also a privacy assurance technique used to prevent privacy leakage by adding noise to the samples [28–30].”
MethodHabbal, A., Ali, M. K., & Abuzaraida, M. A. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122442 · Cited by 407
Camilleri, M. A. (2024) · Expert Systems · doi:10.1111/exsy.13406 · Cited by 331
Local differential privacy and its applications: A comprehensive survey
Yang, M., Guo, T., Zhu, T., Tjuawinata, I., Zhao, J., & Lam, K.-Y. (2024) · Computer Standards & Interfaces · doi:10.1016/j.csi.2023.103827 · Cited by 229
Self-citationDifferential Privacy for Industrial Internet of Things: Opportunities, Applications, and Challenges
Jiang, B., Li, J., Yue, G., & Song, H. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3057419 · Cited by 201
Artificial intelligence in ophthalmology: The path to the real-world clinic
Li, Z., Wang, L., Wu, X., Jiang, J., Qiang, W., Xie, H., Zhou, H., Wu, S., Shao, Y., & Chen, W. (2023) · Cell Reports Medicine · doi:10.1016/j.xcrm.2023.101095 · Cited by 188
Adversarial Attacks and Defenses in Deep Learning: From a Perspective of Cybersecurity
Zhou, S., Liu, C., Ye, D., Zhu, T., Zhou, W., & Yu, P. S. (2022) · ACM Computing Surveys · doi:10.1145/3547330 · Cited by 244
“For example, due to the advantageous properties of differential privacy, it can also contribute to stabilize learning [146] or build heuristic models for game-theoretic solutions [147, 148].”
BackgroundSelf-citationXu, H., Zhu, T., Zhang, L., Zhou, W., & Yu, P. S. (2024) · ACM Computing Surveys · doi:10.1145/3603620 · Cited by 164
“Differential privacy [17, 18] guarantees that by looking at a model output, one cannot tell whether a sample is in the training dataset or not.”
BackgroundSelf-citationFedRecovery: Differentially Private Machine Unlearning for Federated Learning Frameworks
Zhang, L., Zhu, T., Zhang, H., Xiong, P., & Zhou, W. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3297905 · Cited by 175
“The aim of differential privacy is to bound the differences in a query between two datasets that differ in a single entry [37].”
BackgroundSelf-citationFrom distributed machine learning to federated learning: In the view of data privacy and security
Shen, S., Zhu, T., Wu, D., Wang, W., & Zhou, W. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6002 · Cited by 142
Self-citationPrivacy and Artificial Intelligence
Curzon, J., Kosa, T. A., Akalu, R., & El‐Khatib, K. (2021) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3088084 · Cited by 147
A Robust Game-Theoretical Federated Learning Framework With Joint Differential Privacy
Zhang, L., Zhu, T., Xiong, P., Zhou, W., & Yu, P. S. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3140131 · Cited by 111
“Recently, differential privacy has also been proven to provide useful game-theoretic properties in AI fields [31].”
BackgroundSelf-citationFouda, M. M., Fadlullah, Z. M., Ibrahem, M. I., & Kato, N. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3486690 · Cited by 122
“DP can be applied to various tasks such as data mining, ML, and statistical analysis [142], [143], [144].”
Trusted AI in Multiagent Systems: An Overview of Privacy and Security for Distributed Learning
Ma, C., Li, J., Wei, K., Liu, B., Ding, M., Yuan, L., Han, Z., & Vincent Poor, H. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3306773 · Cited by 96
“Thus, using DP to achieve fairness may be a solution [255].”
MethodAdversarial Attacks Against Deep Generative Models on Data: A Survey
Sun, H., Zhu, T., Zhang, Z., Jin, D., Xiong, P., & Zhou, W. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130903 · Cited by 90
“Federated GANs have received much attention, with some researchers try to build more confidential models that offer formal differential privacy guarantees [122].”
Self-citationMachine learning in marketing: Recent progress and future research directions
Herhausen, D., Bernritter, S. F., Ngai, E. W. T., Kumar, A., & Delen, D. (2023) · Journal of Business Research · doi:10.1016/j.jbusres.2023.114254 · Cited by 124
One Parameter Defense—Defending Against Data Inference Attacks via Differential Privacy
Ye, D., Shen, S., Zhu, T., Liu, B., & Zhou, W. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3163591 · Cited by 116
Self-citationToward a Comprehensive Framework for Ensuring Security and Privacy in Artificial Intelligence
Villegas-Ch, W. E., & García-Ortiz, J. (2023) · Electronics · doi:10.3390/electronics12183786 · Cited by 129
Federated learning-empowered smart manufacturing and product lifecycle management: A review
Leng, J., Li, R. C., Xie, J., Zhou, X., Li, X., Liu, Q., Chen, X., Shen, W., & Wang, L. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103179 · Cited by 101
From distributed machine learning to federated learning: In the view of data privacy and security
Shen, S., Zhu, T., Wu, D., Wang, W., & Zhou, W. (2021) · UTS ePRESS (University of Technology Sydney) · Cited by 82
Self-citationPrivacy Intelligence: A Survey on Image Privacy in Online Social Networks
Liu, C., Zhu, T., Zhang, J., & Zhou, W. (2022) · ACM Computing Surveys · doi:10.1145/3547299 · Cited by 102
“Recently, diferential privacy (DP) [71], a mathematical mechanism for measuring the privacy loss led by data publishing, has been studied for visual obfuscation.”
BackgroundSelf-citationPrivacy preservation in Artificial Intelligence and Extended Reality (AI-XR) metaverses: A survey
Alkaeed, M., Qayyum, A., & Qadir, J. (2024) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2024.103989 · Cited by 103
Event detection in online social network: Methodologies, state-of-art, and evolution
Hu, X., Ma, W., Chen, C., Wen, S., Zhang, J., Xiang, Y., & Fei, G. (2022) · Computer Science Review · doi:10.1016/j.cosrev.2022.100500 · Cited by 73
Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey
Liu, J., Du, Y., Yang, K., Wu, J., Wang, Y., Hu, X., Wang, Z., Liu, Y., Sun, P., Boukerche, A., et al. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2026.3669216 · Cited by 152
“…suites to standardize evaluation and foster collaborative innovation; and (4) Investigating cross-layer optimizations that jointly consider AI models and emerging technologies like 6G, neuromorphic computing, and quantum edge computing to unlock new frontiers in distributed intelligence.”
Artificial Intelligence Applications in Healthcare Sector: Ethical and Legal Challenges
Chikhaoui, E., Alajmi, A., & Larabi-Marie-Sainte, S. (2022) · Emerging Science Journal · doi:10.28991/esj-2022-06-04-05 · Cited by 102
Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
Demelius, L., Kern, R., & Trügler, A. (2025) · ACM Computing Surveys · doi:10.1145/3712000 · Cited by 111
“…reviews mentioned in Table 1, a range of broader reviews exist, such as those about differentially private machine learning (without focusing on DL) [22, 64, 151], privacy-preserving DL (without focusing on DP) [24, 32, 68, 89, 117, 124], or privacy-preserving machine learning in general [82, 135].”
Privacy, accuracy, and model fairness trade-offs in federated learning
Gu, X., Tianqing, Z., Li, J., Zhang, T., Ren, W., & Choo, K.-K. R. (2022) · Computers & Security · doi:10.1016/j.cose.2022.102907 · Cited by 53
When AI Meets Information Privacy: The Adversarial Role of AI in Data Sharing Scenario
Majeed, A., & Hwang, S. O. (2023) · IEEE Access · doi:10.1109/access.2023.3297646 · Cited by 71
“However, its amalgamation with the DP can contribute to handling different types of privacy threats, such as inference attacks or membership attacks in AI environments [48], [49].”
BackgroundVisual privacy attacks and defenses in deep learning: a survey
Zhang, G., Liu, B., Zhu, T., Zhou, A., & Zhou, W. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10123-y · Cited by 60
Self-citationA Game-Theoretic Method for Defending Against Advanced Persistent Threats in Cyber Systems
Zhang, L., Zhu, T., Hussain, F. K., Ye, D., & Zhou, W. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3229595 · Cited by 56
“Game theory is the study of strategic interactions between rational decision makers [18].”
BackgroundSelf-citationDifferential privacy in deep learning: Privacy and beyond
Wang, Y., Wang, Q., Zhao, L., & Wang, C. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.06.010 · Cited by 65
A Differentially Private Game Theoretic Approach for Deceiving Cyber Adversaries
Ye, D., Zhu, T., Shen, S., & Zhou, W. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3016842 · Cited by 42
“Differential privacy has been successfully applied to cyber physical systems [31], machine learning [32] and artificial intelligence [33], [34].”
BackgroundSelf-citationEnhancing Data Privacy: A Comprehensive Survey of Privacy-Enabling Technologies
Razi, Q., Piyush, R., Chakrabarti, A., Singh, A., Hassija, V., & Chalapathi, G. (2025) · IEEE Access · doi:10.1109/access.2025.3546618 · Cited by 47
“Additionally, the advent of technologies such as Artificial Intelligence (AI) and Machine Learning (ML) has intensified the risk of data breaches, as these technologies can analyze data at an unprecedented scale, often without the knowledge or consent of authors [7].”
InfluentialModel Poisoning Defense on Federated Learning: A Validation Based Approach
Wang, Y., Zhu, T., Chang, W., Shen, S., & Ren, W. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-65745-1_12 · Cited by 44
Self-citationDifferentially Private Demand Side Management for Incentivized Dynamic Pricing in Smart Grid
Hassan, M. U., Rehmani, M. H., Du, J. T., & Chen, J. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3157472 · Cited by 40
Security, privacy, and robustness for trustworthy AI systems: A review
Saeed, M. M., & Alsharidah, M. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109643 · Cited by 54
Integrating a Blockchain-Based Governance Framework for Responsible AI
Asif, R., Hassan, S. R., & Parr, G. P. (2023) · Future Internet · doi:10.3390/fi15030097 · Cited by 54
Liu, X., Wang, J., Xiong, X., & Sun, H. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128653 · Cited by 39
Artificial intelligence in ophthalmology: Progress, challenges, and ethical implications
Savastano, M. C., Rizzo, C., Fossataro, C., Bacherini, D., Giansanti, F., Savastano, A., Arcuri, G., Rizzo, S., & Faraldi, F. (2025) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2025.101374 · Cited by 52
Privacy preservation for image data: A GAN‐based method
Chen, Z., Zhu, T., Xiong, P., Wang, C., & Ren, W. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22356 · Cited by 33
“19,20 In terms of image privacy preservation, Fan was the first to extend the concept of differential privacy with a scheme of sharing pixelized images, 21 while Yuan et al. applied differential privacy to medical images.”
BackgroundSelf-citationBoosting Model Inversion Attacks With Adversarial Examples
Zhou, S., Zhu, T., Ye, D., Yu, X., & Zhou, W. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3285015 · Cited by 42
“Existing defense strategies against model inversion attacks tend to decrease the dependency between inputs and outputs during classifiers’ training [33], [34], [35], [36].”
BackgroundSelf-citationXue, L., & Zhu, T. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107568 · Cited by 40
Self-citationNew challenges in reinforcement learning: a survey of security and privacy
Lei, Y., Ye, D., Shen, S., Sui, Y., Zhu, T., & Zhou, W. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10348-5 · Cited by 39
“Differential privacy can be used in learning problems to improve various aspects of a model, such as randomization, privacy preservation capability, and algorithm stability (Zhu et al. 2020).”
BackgroundSelf-citationHang, C. N., Tsai, Y.-Z., Yu, P.-D., Chen, J., & Tan, C. W. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7020108 · Cited by 38
Self-citationGutti, C., Thumula, K., & Parag, B. (2025) · IEEE Access · doi:10.1109/access.2025.3592481 · Cited by 56
“The challenge, therefore, lies in tuning these methods to maintain high detection performance while ensuring strong privacy guarantees [23].”
Differential Advising in Multiagent Reinforcement Learning
Ye, D., Zhu, T., Cheng, Z., Zhou, W., & Yu, P. S. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3034424 · Cited by 31
Self-citationLiang, J., Sadiq, M., Yang, G., Jiang, K., Cai, T., & Ma, M. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108862 · Cited by 35
FRAMU: Attention-Based Machine Unlearning Using Federated Reinforcement Learning
Shaik, T., Tao, X., Li, L., Xie, H., Cai, T., Zhu, X., & Li, Q. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3382726 · Cited by 45
“While privacy has been partially addressed through Differential Privacy [30] and Secure Multiparty Computation [31], these techniques often compromise on model efficiency.”
BackgroundKuppan, K., Acharya, D. B., & Divya, B. (2024) · IEEE Access · doi:10.1109/access.2024.3509918 · Cited by 62
APSM: Adaptive privacy budget control in differentially private matching in electric vehicles
Masood, S., Hassan, M. U., Tsai, P., Zhang, K., Gao, L., Dong, M., & Chen, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130453 · Cited by 28
Preserving data privacy in federated learning through large gradient pruning
Zhang, Z., Zhu, T., Ren, W., Xiong, P., & Choo, K. R. (2022) · Computers & Security · doi:10.1016/j.cose.2022.103039 · Cited by 38
Self-citationWhen deep learning meets watermarking: A survey of application, attacks and defenses
Chen, H., Liu, C., Zhu, T., & Zhou, W. (2024) · Computer Standards & Interfaces · doi:10.1016/j.csi.2023.103830 · Cited by 34
Self-citationWorkplace security and privacy implications in the GenAI age: A survey
Diro, A. A., Kaisar, S., Saini, A., Fatima, S., Pham, H., & Erba, F. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103960 · Cited by 57
A Game-Theoretic Federated Learning Framework for Data Quality Improvement
Zhang, L., Zhu, T., Xiong, P., Zhou, W., & Yu, P. S. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3230959 · Cited by 33
“Recently, differential privacy has also been proven to provide useful game-theoretic properties in the area of artificial intelligence [27].”
BackgroundSelf-citationAlrubayyi, H., Alshareef, M. S., Nadeem, Z., Abdelmoniem, A. M., & Jaber, M. (2024) · Future Internet · doi:10.3390/fi16030085 · Cited by 29
More than Privacy: Adopting Differential Privacy in Game-theoretic Mechanism Design
Zhang, L., Zhu, T., Xiong, P., Zhou, W., & Yu, P. S. (2021) · ACM Computing Surveys · doi:10.1145/3460771 · Cited by 39
“Over the past decade, differential privacy has been widely employed in data science [125] and AI [15, 127].”
BackgroundSelf-citationDifferentially Private Crowdsourcing With the Public and Private Blockchain
Wang, M., Zhu, T., Zuo, X., Yang, M., Yu, S., & Zhou, W. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3233360 · Cited by 27
“Various techniques, such as dummy locations [7] and differential privacy [8], [9], have been proposed to overcome the privacy problem in crowdsourcing systems.”
BackgroundSelf-citationFederated Learning for 6G Networks: Navigating Privacy Benefits and Challenges
Sandeepa, C., Zeydan, E., Samarasinghe, T., & Liyanage, M. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3513832 · Cited by 41
A review of multi-modal deep learning towards agentic smart manufacturing
Leng, J., Wang, J., Zhou, L., Zhao, R., Chen, C., Zhang, D., Zheng, S., Liu, Q., & Shen, W. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104117 · Cited by 31
Building trust in robo-advisory: technology, firm-specific and system trust
Cao, X., de Zwaan, L., & Wong, V. (2025) · Qualitative Research in Financial Markets · doi:10.1108/qrfm-02-2024-0033 · Cited by 38
A Review of Power System False Data Attack Detection Technology Based on Big Data
Chang, Z., Wu, J., Liang, H., Wang, Y., Wang, Y., & Xiong, X. (2024) · Information · doi:10.3390/info15080439 · Cited by 27
Differential privacy and artificial intelligence: potentials, challenges, and future avenues
Alzoubi, Y. I., & Mishra, A. (2025) · EURASIP Journal on Information Security · doi:10.1186/s13635-025-00203-9 · Cited by 29
“This flexibility contributes to ensuring fairness throughout the model’s existence [48].”
InfluentialZhou, W., Zhu, T., Ye, D., Ren, W., & Choo, K. R. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3312118 · Cited by 30
“These generally yield better performance, but they do not work well in settings where privacy protection is mandated [3], such as in Europe, with the General Data Protection Regulation [4].”
BackgroundSelf-citationZhang, X., Wang, Q., Yu, J., Sun, Q., Hu, H., & Liu, X. (2023) · Electronics · doi:10.3390/electronics12234763 · Cited by 27
“On the other hand, DP methods involve simple operations, such as data perturbation and noise injection [43].”
MethodSagar, A. S. M. S., Haider, A., & Kim, H. S. (2024) · Computer Communications · doi:10.1016/j.comcom.2024.107969 · Cited by 30
Time-optimal and privacy preserving route planning for carpool policy
Zhu, C., Ye, D., Zhu, T., & Zhou, W. (2022) · World Wide Web · doi:10.1007/s11280-022-01026-1 · Cited by 19
“Current online route planning services require the precise location of users [32].”
BackgroundSelf-citationSei, Y., Onesimu, J. A., & Ohsuga, A. (2022) · IEEE Access · doi:10.1109/access.2022.3208715 · Cited by 21
“Many differential privacy methods use the Laplace mech- 221 anism for numerical attributes [9].”
BackgroundMethodInfluentialUpdate Selective Parameters: Federated Machine Unlearning Based on Model Explanation
Xu, H. Y., Zhu, T., Zhang, L., Zhou, W., & Yu, P. S. (2024) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2024.3409947 · Cited by 26
“To further improve the security of the training process, our scheme is also compatible with other schemes, such as differential privacy [25].”
Self-citationMulti‐agent reinforcement learning via knowledge transfer with differentially private noise
Cheng, Z., Ye, D., Zhu, T., Zhou, W., Yu, P. S., & Zhu, C. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22648 · Cited by 20
“Based on Zhu and Yu's work, 22 Ye et al. 23,24 proposed two differentially private frameworks for use by multi ‐ agent system to overcome malicious agents and overhead communication.”
BackgroundSelf-citationPrivacy Data Propagation and Preservation in Social Media: A Real-World Case Study
Hu, X., Zhu, T., Zhai, X., Zhou, W., & Zhao, W. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3137326 · Cited by 18
“Insocial media, privacy has multiple meanings in different situations and data format [10].”
BackgroundSelf-citationDefense against membership inference attack in graph neural networks through graph perturbation
Wang, K., Wu, J., Zhu, T., Ren, W., & Hong, Y. (2022) · International Journal of Information Security · doi:10.1007/s10207-022-00646-y · Cited by 19
Self-citationCorrelated data in differential privacy: Definition and analysis
Zhang, T., Zhu, T., Liu, R. P., & Zhou, W. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6015 · Cited by 21
Self-citationFair Federated Learning with Opposite GAN
Han, M., Zhu, T., & Zhou, W. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111420 · Cited by 23
Self-citationA survey on machine unlearning: Techniques and new emerged privacy risks
Liu, H., Xiong, P., Zhu, T., & Yu, P. S. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104010 · Cited by 45
Self-citationPerdana, A., Arifin, S., & Quadrianto, N. (2025) · Technology in Society · doi:10.1016/j.techsoc.2025.102838 · Cited by 43
AI-generated content in cross-domain applications: Research trends, challenges and propositions
Li, J., Qu, L., Cai, T., Zhao, Z., Haldar, N. A. H., Krishna, A., Kong, X., Macau, F., Chakraborty, T., Deroy, A., et al. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114634 · Cited by 34
“Privacy-preserving technologies [177, 178, 179] constitute a primary approach to address data sovereignty and security risks in generative AI.”
Reveal Your Images: Gradient Leakage Attack Against Unbiased Sampling-Based Secure Aggregation
Yang, Y., Ma, Z., Xiao, B., Liu, Y., Li, T., & Zhang, J. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3271432 · Cited by 16
“More importantly, different from general differential privacy-based protection [10], [11], [12] or Top-k compression, the crafted random transformation of UGS is unbiased, and hence, causes minimized performance degradation of the trained model.”
BackgroundAli, S. A. M., Metwally, A. B. M., & Mohamed, A. T. I. (2024) · ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS) · doi:10.1109/icetsis61505.2024.10459587 · Cited by 18
Georges-Filteau, J., & Cirillo, E. (2020) · doi:10.22541/au.158921777.79483839/v2 · Cited by 25
“…et al., 2019; Goncalves et al., 2020; Torfi and Beyki, 2019; Frid-Adar et al., 2018; Ozyigit et al., 2020; Yang et al., 2019c; Yoon et al., 2020; Zhu et al., 2020a; Yoon et al., 2020; Walsh et al., 2020; Yale et al., 2019a; Ozyigit et al., 2020; Dash et al., 2019; Bae et al., 2020b).”
BackgroundMethodInfluentialAttribute-Based Membership Inference Attacks and Defenses on GANs
Sun, H., Zhu, T., Li, J., Ji, S., & Zhou, W. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3305591 · Cited by 16
Self-citationZia, M. F., Furqan, H. M., & Hamamreh, J. M. (2021) · doi:10.46470/03d8ffbd.08b7bd1d · Cited by 14
“THz technology has the problem of authentication [18] and malicious behavior [19], and finally VLC is again prone to communication [20] and malicious behavior problem [21].”
BackgroundXu, G., Dong, C., & Meng, L. (2022) · Sustainability · doi:10.3390/su142114002 · Cited by 12
Location-Based Real-Time Updated Advising Method for Traffic Signal Control
Zhu, C., Ye, D., Zhu, T., & Zhou, W. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3342480 · Cited by 12
“The efficacy of reinforcement learning is heavily dependent on the caliber of feature selection [9].”
BackgroundSelf-citationGeoLocator: A Location-Integrated Large Multimodal Model (LMM) for Inferring Geo-Privacy
Yang, Y., Wang, S., Li, D., Sun, S., & Wu, Q. (2024) · Applied Sciences · doi:10.3390/app14167091 · Cited by 23
Vertical Federated Unlearning via Backdoor Certification
Han, M., Zhu, T., Zhang, L., Huo, H., & Zhou, W. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3536312 · Cited by 15
“Addressing privacy concerns, there are also comprehensive surveys on differential privacy, including various attack and defense mechanisms, as discussed in recent studies [9], [10].”
Self-citationPrivacy 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
DPPT : A differential privacy preservation technique for cyber–physical system
Basak, S., Chatterjee, K., & Singh, A. P. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108661 · Cited by 16
Time-Driven and Privacy-Preserving Navigation Model for Vehicle-to-Vehicle Communication Systems
Zhu, C., Cheng, Z., Ye, D., Hussain, F. K., Zhu, T., & Zhou, W. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3248613 · Cited by 11
Self-citationGeo-Perturbation for Task Allocation in 3-D Mobile Crowdsourcing: An A3C-Based Approach
Min, M., Zhu, H., Yang, S. H., Xu, J., Tong, J., Li, S., & Shu, J. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3295786 · Cited by 13
“Based on differential privacy, the location perturbation mechanism can offer robust protection against prior knowledge adversaries and ensure location privacy through a rigorous verification process [25].”
BackgroundA privacy preservation method for multiple-source unstructured data in online social networks
Wang, C., Zhu, T., Xiong, P., Ren, W., & Choo, K. R. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102574 · Cited by 12
Self-citationInvestigating Trade-offs in Utility, Fairness and Differential Privacy in Neural NetworksPreprint
Pannekoek, M., & Spigler, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05975 · Cited by 34
“Finally, fairness entails that the behavior of a machine learning system does not dependent on protected attributes such as race and gender (Zhu et al., 2020).”
BackgroundOladele, R. I., Orelaja, A., & Akinwande, O. T. (2024) · International Journal of Latest Technology in Engineering Management & Applied Science · doi:10.51583/ijltemas.2024.130207 · Cited by 22
The Pillars of AI Ethics: Transparency, Accountability, and Privacy
Ramya, R., Priya, S. B., Thamizhikkavi, P., & Anand, M. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9173-0.ch004 · Cited by 14
A Survey on Privacy-Enhancing Techniques in the Era of Artificial Intelligence
Dritsas, E., Τρίγκα, Μ., & Phivos Mylonas, B. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-73344-4_32 · Cited by 9
Blockchain controlled trustworthy federated learning platform for smart homes
Biswas, S., Sharif, K., Latif, Z., Alenazi, M. J. F., Pradhan, A. K., & Bairagi, A. K. (2024) · IET Communications · doi:10.1049/cmu2.12870 · Cited by 9
Both ends of artificial intelligence impacting privacy: a review of violation and protection
Voloch, N., & Hirschprung, R. S. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1686454 · Cited by 16
PRIMϵ: Novel Privacy-Preservation Model With Pattern Mining and Genetic Algorithm
Madhusudhanan, S., Jose, A. C., Sahoo, J., & Malekian, R. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3324769 · Cited by 10
“Unlike existing techniques that induce noise in accordance with static evaluation of query sensitivity [74], [75], GA PRIM ϵ yields an adaptive ϵ without any manual intervention.”
MethodNaresh, V. S., Raju, A. V., & Rao, O. S. (2025) · Wiley Interdisciplinary Reviews Computational Statistics · doi:10.1002/wics.70046 · Cited by 16
“Moreover, combining differential privacy with artificial intelligence has demonstrated potential for tackling new challenges, including privacy breaches, security issues, and ensuring model fairness (Zhu and Yu 2019; Zhu, Ng, and Mong Goh 2020; Zhu, Ye, et al. 2020).”
Leveraging Artificial Intelligence and Machine Learning for Enhanced Privacy and Security
Rani, S., Kumar, N., Srivastva, A., & Sharma, A. (2024) · IEEE International Conference on Blockchain and Distributed Systems Security (ICBDS) · doi:10.1109/icbds61829.2024.10837569 · Cited by 8
“Zhu et al., [19] This research demonstrates that differential privacy is useful for purposes beyond maintaining privacy.”
Differentially private GANs for generating synthetic indoor location data
Moghtadaiee, V., Alishahi, M., & Rabiei, M. (2025) · International Journal of Information Security · doi:10.1007/s10207-025-01020-4 · Cited by 11
“This implies that the generator has the ability to recall training samples by means of deep neural networks.”
Metadata
- Authors
- Zhu, T., Ye, D., Wang, W., Zhou, W., & Yu, P. S.
- Affiliations
- China University of Geosciences (CN)
- University of Technology Sydney (AU)
- University of Illinois Chicago (US)
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2022-06-01
- Volume
- 34
- Issue
- 6
- Pages
- 2824-2843
- ISSN
- 1041-4347 (ISSN-L)
- 1558-2191
- 2326-3865
- OpenAlex
- W3047327820
- Semantic Scholar
- 7d5b94f9d2cee5823757352155d0234454f09a0e
- Cited by
- 219
- References
- 152
- Citations by year
- 2026: 27 · 2025: 64 · 2024: 45 · 2023: 36 · 2022: 23
- FWCI
- 8.08
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- IEEE Transactions on Knowledge and Data Engineering (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- OPUS - Open Publications of UTS Scholars (University of Technology Sydney) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61972366)
- National Science Foundation (III-1526499, III-1763325, III-1909323, SaTC-1930941)
- Australian Research Council Discovery (DP190100981)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection
- Keywords
- differential privacy, privacy preservation, machine learning security, model fairness, distributed learning, deep learning, multi-agent systems, learning stability, privacy-utility trade-off
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.