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
Items 101–200 of 219
Razi, A., Bouzoubaa, L. A., Pessianzadeh, A., Seberger, J. S., & Rezapour, R. (2025) · Research Square · doi:10.21203/rs.3.rs-5686084/v1 · Cited by 14
Shafee, A. A., Mahmoud, M. M. E. A., Bruce, J. W., Srivastava, G., Balamsh, A., & Aljohani, A. J. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3299522 · Cited by 7
“3) Differential Privacy ( DP ): Differential privacy [34] is originally introduced for preserving privacy in the applications that retrieve aggregated statistics from databases.”
BackgroundArtificial Intelligence in Marketing: Concerns and Solutions
Alammal, A. H., & Mubarak, M. A. (2023) · Internet of things · doi:10.1007/978-3-031-35525-7_7 · Cited by 8
Multi-Agent Reinforcement Learning for Online Food Delivery with Location Privacy Preservation
Abahussein, S., Ye, D., Zhu, C., Cheng, Z., Siddique, U., & Shen, S. (2023) · Information · doi:10.3390/info14110597 · Cited by 7
Self-citationSelective Privacy-Preserving Federated Learning for Large Language Model Fine-Tuning
Pan, Q., & Wu, J. (2025) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc65282.2025.11059634 · Cited by 8
A location-based advising method in teacher–student frameworks
Zhu, C., Ye, D., Huo, H., Zhou, W., & Zhu, T. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111333 · Cited by 6
Self-citationGenerative Adversarial Privacy for Multimedia Analytics Across the IoT-Edge Continuum
Wang, X., Lv, J., Kim, B., Maple, C. R., Parameshachari, B. D., Słowik, A., & Li, K. (2024) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2024.3459789 · Cited by 6
“This oversight highlights a crucial need for developing robust privacy protection strategies tailored for multimedia data in IoT-Edge ecosystems, ensuring that technological progress does not come at the cost of individual privacy and data security [17].”
Defending against attacks in deep learning with differential privacy: a survey
Xiangfei, Z., & Qingchen, Z. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11350-3 · Cited by 12
“Zhu et al. (2022 ) discussed the key areas for applying DP to artificial intelligence and summarized the relevant research progress and application cases.”
Privacy Protection Technology Based on Machine Learning and Intelligent Data Recognition
liu, Q. (2022) · Security and Communication Networks · doi:10.1155/2022/1598826 · Cited by 7
“'us, there are many limitations to current privacy attacks on machine learning, and such attacks can only succeed under certain circumstances [13].”
BackgroundRetractedEvent-set differential privacy for fine-grained data privacy protection
Wang, T., Yang, W., Ma, X., & Wang, B. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.10.006 · Cited by 6
Learning to Design Fair and Private Voting Rules
Mohsin, F., Liu, A., Chen, P., Rossi, F., & Xia, L. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13734 · Cited by 6
“However, work in differential privacy literature has suggested that the randomization required for privacy may be applied in ways to also preserve like fairness (e.g., in (Zhu et al., 2022)).”
BackgroundShui, X., Lv, Y., Yuan, R. B., Zhang, K., Yang, X., & Gedikli, E. D. (2025) · Measurement · doi:10.1016/j.measurement.2025.118981 · Cited by 5
A Membership Inference and Adversarial Attack Defense Framework for Network Traffic Classifiers
Liu, G., Zhang, W., Wang, X., King, S., & Yu, S. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3357791 · Cited by 8
“When applied to network traffic classifiers, these defenses not only exhibit poor protection performance but also yield a significant drop in ACC [8], [9].”
Linkage on security, privacy and fairness in federated learning: New balances and new perspectives
Wang, L., Zhu, T., Zhou, W., & Yu, P. S. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107874 · Cited by 12
Self-citationResearch on Improvement of the Click-Through Rate Prediction Model Based on Differential Privacy
Tian, L., Ge, L., Wang, Z., Zhang, G., Xu, C., & Qin, X. (2022) · IEEE Access · doi:10.1109/access.2022.3215265 · Cited by 5
“Zhu et al. [21] pointed out that adding noise to the dataset is the most straightforward and effective approach; however, this approach affects the utility of the learned model because it heavily relies on attribute values in the training dataset.”
BackgroundCross-Domain Transformation for Outlier Detection on Tabular Datasets
Herurkar, D., Sattarov, T., Hees, J., Palacio, S., Raue, F., & Dengel, A. R. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191326 · Cited by 8
“A recent overview of the field can be found in surveys such as [14], [15] and was amongst others applied to Federated-Learning [16] and Deep Learning [17].”
MethodAn Improved Genetic Algorithm for Safety and Availability Checking in Cyber-Physical Systems
Wang, Z., Jin, Y., Yang, S., Han, J., & Lu, J. (2021) · IEEE Access · doi:10.1109/access.2021.3072635 · Cited by 5
“It prevent a set of users less than a certain threshold from being fully authorized to perform sensitive tasks [15], [16], [20].”
BackgroundEfficient Privacy-Preserving Logistic Model With Malicious Security
Miao, G., & Wu, S. S. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3402319 · Cited by 14
“Differential privacy (DP) [26] has been widely incorporated into distributed deep learning [27], [28], [29] by adding noise to input data, loss functions, gradients, weights, or output classes.”
BackgroundGeorges-Filteau, J., & Cirillo, E. (2020) · Research Square · doi:10.21203/rs.3.rs-116297/v2 · Cited by 7
Ethical issues and coping strategies for artificial intelligence in medical research
Qiu, P., Zhang, H., Han, Y., Lei, J., & Zhang, X. (2025) · Translational dental research. · doi:10.1016/j.tdr.2025.100051 · Cited by 8
Privacy Interventions and Education (PIE): Encouraging Privacy Protective Behavioral Change Online
Smith, G., Chapman, K., Agha, Z., Ruppert, J., Cullen, S., Khan, S., Knijnenburg, B. P., Jessica Vitak, B., Kumar, P. C., Wiśniewski, P., et al. (2023) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3544549.3573816 · Cited by 4
“Recent workshops have also explored evolving privacy needs in newer technical domains, including Artificial Intelligence (AI) [14, 35] and Internet of Things (IoT) technologies [32].”
BackgroundAI-Driven CPU Resource Management in Cloud Operating Systems
Wang, Y., & Xing, S. (2025) · Journal of Computer and Communications · doi:10.4236/jcc.2025.136009 · Cited by 7
Memorization of Named Entities in Fine-Tuned BERT Models
Diera, A., Lell, N., Garifullina, A., & Scherp, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-40837-3_16 · Cited by 6
“Since directly adding noise to DNN parameters may significantly harm its utility, the best and most common place for applying DP in deep learning is the gradients [65].”
A Differentially Private Auction Mechanism in Online Social Networks
Hu, X., Ye, D., Zhu, T., & Huo, H. (2021) · Journal of Systems Science and Systems Engineering · doi:10.1007/s11518-021-5493-5 · Cited by 4
Self-citationMahapatra, C. (2025) · Preprints.org · doi:10.20944/preprints202505.0369.v1 · Cited by 5
Safer Algorithmically-Mediated Offline Introductions: Harms and Protective Behaviors
Rivera, V. A., Wilkinson, D., Augusta, A., Li, S., Redmiles, E. M., & Strohmayer, A. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3686948 · Cited by 6
Pourkabirian, A., Ni, W., Zhou, X., Li, K., & Anisi, M. H. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3579291 · Cited by 3
Zhao, X., Wang, X., Lin, W., Ng, W. W. Y., & Liu, K. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3610241 · Cited by 3
“Recent studies have also demonstrated that malicious adversaries can still infer and extract sensitive privacy information from local models [12], [13], [14], [15].”
Zhao, W., Huang, W. C., Zhang, Z., Jia, M., Xu, W., Peng, J., & Liao, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3613955 · Cited by 4
“D IFFERENTIAL privacy (DP) is widely used in many fields of artificial intelligence (AI) such as machine learning, deep learning, multi-agent systems and so on [1].”
Shi, L., Gao, Y., Chen, C., Huang, S., Zhao, J., & Hu, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3618185 · Cited by 3
“…also possess knowledge related to privacy preservation and could deduce how the gradient was generated based on the statistical features of the privacy pre-servedinformation,[6]includinggradientsprotectedbygradient clipping [11], [22], gradient sparsification [23], [24], [25] and simple DP [26].”
Strategic Integration of AI in Modern Data Management
Divakaran, P., Parnami, T., Gaur, S., Baryah, N., Gupta, K., & Upreti, K. (2025) · World Skills Conference on Universal Data Analytics and Sciences (WorldSUAS) · doi:10.1109/worldsuas66815.2025.11199110 · Cited by 3
“The successful applications of differential privacy have shown that a variety of its features, such as algorithm stability, privacy protection abilities, and randomization, can be applied to address learning challenges [26].”
Li, M., Xiao, D., & Chen, L. (2024) · Signal Processing · doi:10.1016/j.sigpro.2024.109742 · Cited by 5
Toward Efficient Target-Level Machine Unlearning Based on Essential Graph
Xu, H. Y., Zhu, T., Zhang, L., Zhou, W., & Zhao, W. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3514607 · Cited by 6
“Guo et al. [8] proposed certified removal , an unlearning scheme inspired by differential privacy [14].”
Self-citationSun, X., Li, Z. G., & Jiang, C. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3552206 · Cited by 3
“Although some methods in current PFL incorporate di ff erential privacy (DP) [22] to balance model accuracy and user privacy, users often have specific preferences regarding both accuracy and privacy.”
Yadav, P. K., Pandey, S., & Pandey, P. (2025) · International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS) · doi:10.1109/icssas66150.2025.11080921 · Cited by 3
“The mechanism identified in Table III illustrates the mathematical design of an adaptive approach to Differential Privacy (DP) that will be used for processing driver monitoring applications securely [23].”
Migrating federated learning to centralized learning with the leverage of unlabeled data
Wang, X., Zhu, T., Ren, W., Zhang, D., & Xiong, P. (2023) · Knowledge and Information Systems · doi:10.1007/s10115-023-01869-8 · Cited by 4
Self-citationFeature Extraction to Evaluate the Quality of Data Using Machine Learning Technique
Pratheesh, R., & Divya, V. (2024) · International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) · doi:10.1109/icdcece60827.2024.10549606 · Cited by 4
“Data quality [1] analysis is considered as one of the important steps in prediction process.”
BackgroundHow to dissolve the “privacy paradox” in social networks? A game approach based on privacy calculus
Zhang, X., Cai, Y., Liu, F., & Zhou, F. (2024) · Kybernetes · doi:10.1108/k-03-2024-0544 · Cited by 3
A Privacy-Preserving User-Centric Data-Sharing Scheme
Boiarkin, V., Zarpel�ão, B. B., Al-Zaili, J., & Rajarajan, M. (2024) · IEEE Access · doi:10.1109/access.2024.3476209 · Cited by 2
“To preserve end-user privacy, DP-based models are widely used across different domains that include but are not limited to machine learning [6], Industrial Internet of Things [7], and healthcare [8].”
AI in Healthcare Safeguarding Patient Privacy and Confidentiality
Sindiramutty, S. R., Jhanjhi, N. Z., & Khan, N. A. (2025) · Advances in information security, privacy, and ethics book series · doi:10.4018/979-8-3693-6135-1.ch015 · Cited by 2
Application of differential privacy in smart building systems
Teng, Y., Yin, L., Chen, Y., Li, Z., Hu, X., & El‐Sherbeeny, A. M. (2025) · Systems & Control Letters · doi:10.1016/j.sysconle.2025.106144 · Cited by 2
Zareie, S., Esmaeilyfard, R., & Shamsinejadbabaki, P. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/5531568 · Cited by 2
Shojaei, P., Zameni, N., & Moieni, R. (2025) · Open Journal of Social Sciences · doi:10.4236/jss.2025.138004 · Cited by 2
Privacy considerations for LLMs and other AI models: an input and output privacy approach
Nie, Z., Dave, L., & Lewis, R. (2025) · Frontiers in Communications and Networks · doi:10.3389/frcmn.2025.1600750 · Cited by 3
Recent advances in corneal specular microscopy image analysis through artificial intelligence
Marrugo, A. G., Quintero, F. J., Tello, A., Prada, A. M., Galvis, V., & Romero, L. A. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001305 · Cited by 4
“Key obstacles include difficulties in generalizing AI systems across diverse clinical environments and navigating the ethical and legal complexities associated with medical data sharing [71].”
Analysing the Quality and Management of Data in Big Data
Pratheesh, R., & Divya, V. (2024) · International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) · doi:10.1109/icdcece60827.2024.10548691 · Cited by 2
Dasgupta, R., Mekala, S. H., Jaigirdar, F. T., Anwar, A., & Chang, L. Y. C. (2025) · AI & Society · doi:10.1007/s00146-025-02350-6 · Cited by 3
Ensuring Truthfulness in Distributed Aggregative Optimization
Chen, Z., Egerstedt, M., & Wang, Y. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3606265 · Cited by 3
“The basic idea is to make the un-truthful information shared by an agent have a negligible influence on the decisions of other agents, thereby limiting the benefit that an untruthful agent can gain [31]–[33].”
Hiwase, K., Verma, P., Zade, N. R., Kumar, P., Weerarathna, I. N., & Gundewar, S. K. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01164-8 · Cited by 2
Motghare, S., & Nair, P. S. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i3s.6151 · Cited by 2
Providing Highest Privacy Preservation Scenario for Achieving Privacy in Confidential Data
Jain, P., Thada, V., & Motwani, D. (2024) · International Journal of experimental research and review · doi:10.52756/ijerr.2024.v39spl.015 · Cited by 3
Test & Evaluation Best Practices for Machine Learning-Enabled SystemsPreprint
Chandrasekaran, J., Cody, T., McCarthy, N., Lanus, E., & Freeman, L. E. B. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4862589 · Cited by 14
AIM and the Patient’s Perspective
Taylor, D. G. (2021) · Springer eBooks · doi:10.1007/978-3-030-58080-3_37-1 · Cited by 1
Strict Differentially Private Support Vector Machines with Dimensionality Reduction
Wang, T., Liu, S., Liang, J., Wang, S., Wang, L., & Song, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-99-9785-5_11 · Cited by 1
Patel, N. J., & Jadhav, A. (2024) · IET Cyber-Physical Systems Theory & Applications · doi:10.1049/cps2.12100 · Cited by 1
Trust Dynamics in the Digital Economy: Ethical AI and Data Governance Frameworks
Shah, S. S. (2024) · Premier Journal of Artificial Intelligence · doi:10.70389/pjai.100005 · Cited by 5
Long-Term Privacy-Preserving Incentive Scheme Design for Federated Learning
Liu, X., Wang, R., Zhang, P.-F., Xie, L., Liu, Y., Su, Z., Liu, D., & Chang, Y. (2024) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom63139.2024.00377 · Cited by 1
“Although FL holds significant potential for practical applications, existing research shows that the transmission of local model updates to the FL server is susceptible to privacy attacks, such as inference attacks, which can result in privacy breaches on the client side [3], [4].”
Statistical test-based adversarial client detection in federated learning under poisoning attacks
Zhu, H.-T., Huang, W., & Zhang, Z.-L. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103569 · Cited by 4
Zhao, W., Zhang, Z., Huang, W. C., Peng, J., Xu, W., Liao, Y., & Liu, C. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3586056 · Cited by 1
“Fortunately,AImodelscanbetrained withDPmechanisms[9],whichcanreducetheinformation leakageofAImodels.”
PrivGraph: Modeling Personal Privacy Information Using Knowledge Graph
Zuo, J., & Lee, S. (2025) · IEEE International Conference on Software Quality, Reliability and Security (QRS) · doi:10.1109/qrs65678.2025.00080 · Cited by 4
“• Differential privacy [14].”
MetaDP-HE: Dynamic Privacy-Protection With Meta-Model in End-Edge-Cloud Systems
Jiang, B., Niu, M., Luo, F., Wang, H. H., & Song, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3621433 · Cited by 1
“DP [23], [24], which quantifiably controls the privacy budget by adding random noise to data or model parameters, is widely used in distributed learning scenarios under the end-edge-cloud architecture to protect sensitive information.”
A Large Language Model Agent-Guided Multi-agent System for Adaptive Traffic Signal Control
Zhu, M., & Zhu, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3001-4_5 · Cited by 1
Not a Swiss Army Knife: Academics' Perceptions of Trade‐Offs around Generative AI Use
Razi, A., Bouzoubaa, L. A., Pessianzadeh, A., Seberger, J. S., & Rezapour, R. (2025) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.1277 · Cited by 5
Healthcare Security using Federated Learning and Explainable AI with Secure Aggregation
Mukhila, R., Sundhari, M., Nandeta, S., & Pavithra, S. (2025) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscn67106.2025.11308245 · Cited by 1
Zhao, Y., Wang, C., Hao, Q., Lin, H., & Song, Y. (2026) · Computer Standards & Interfaces · doi:10.1016/j.csi.2026.104145 · Cited by 1
Enhancing User Privacy in Natural Language Processing (NLP) Systems
Behera, C. K., Lakshmi, D., & Kondurkar, I. (2023) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-0502-7.ch009 · Cited by 1
Navigating the Ethical Maze: Strengthening AI Integrity in the Philippines
Bibangco, E. J. P. (2024) · Philippine Journal of Science Engineering and Technology · doi:10.63179/pjset.v1i1.44 · Cited by 1
Georges-Filteau, J., & Cirillo, E. (2020) · Research Square · doi:10.21203/rs.3.rs-116297/v1 · Cited by 5
AI Safety in Computer-Assisted Language Learning
Kohnke, L. (2025) · Springer eBooks · doi:10.1007/978-3-031-51447-0_95-1 · Cited by 1
RECENT PROGRESS OF DIFFERENTIALLY PRIVATE FEDERATED LEARNING WITH THE SHUFFLE MODEL
Ahmed, M. A. M., Wu, S., Dushime, L. D., & Tao, Y.-H. (2021) · International Journal of Engineering Technologies and Management Research · doi:10.29121/ijetmr.v8.i11.2021.1028
AIM and the Patient’s Perspective
Taylor, D. G. (2022) · Springer eBooks · doi:10.1007/978-3-030-64573-1_37
Georges-Filteau, J., & Cirillo, E. (2022) · Research Square · doi:10.21203/rs.3.rs-116297/v3 · Cited by 1
Chiu, C.-C., Tsai, P., & Yang, C. (2023) · Wireless Communications and Mobile Computing · doi:10.1155/2023/5303329
“If there is no way to guarantee data security, allowing data queries over autonomous data services by masking sensitive content is an option [17, 18].”
BackgroundJani, K. A., Chaubey, N. K., Panchal, E. P., Tripathi, P., & Yagnik, S. B. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-8111-3_27 · Cited by 2
Differentially Private Support Vector Machines with Knowledge Aggregation
Wang, T., Zhang, Y., Liang, J., Wang, S., & Liu, S. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.048115 · Cited by 2
WITHDRAWNPreprint
Tobiloba, B., Kelvin, K., & Tera, T. (2024) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/9byfr
Integrated approach for healthcare data protection and security: A survey
Dixit, R., & Patil, B. M. (2024) · AIP conference proceedings · doi:10.1063/5.0212743
Privacy of Deep Learning Systems: A Penetration Testing FrameworkPreprint
Vayghan, B. J. (2024) · doi:10.36227/techrxiv.172296728.87985494/v1 · Cited by 1
Towards sharper excess risk bounds for differentially private pairwise learning
Kang, Y., Li, J., Liu, Y., & Wang, W. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128610
Self-citationEnhancing Trajectory Data Privacy through Information Gain-Fused Semantic Generalization
Qing, H., Ibrahim, R. B., & Nies, H. W. (2024) · International Conference on Sustainable Expert Systems (ICSES) · doi:10.1109/icses63445.2024.10762992
Encrypted Semantic Communications for Privacy Preserving
Chen, Z., Tao, M., Wang, Z., & Luo, X. (2025) · doi:10.1002/9781394247912.ch16
Kölzer, D., & Just, V. (2025) · Organisationskompetenz Zukunftsfähigkeit · doi:10.1007/978-3-662-68996-7_2
Chandra, S. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9395-6.ch007 · Cited by 2
Lindez-Macarro, M.-E., & Villalba-Romero, F. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9894-4.ch003 · Cited by 1
“Hey Chatgpt, Fund this Startup!” the Financing of Artificial Intelligence Startups in ItalyPreprint
Giaretta, E., & Zen, F. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5225169
Munir, B. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5198259
Wang, D., Shang, L., & Zhang, Y. (2025) · Springer eBooks · doi:10.1007/978-3-031-90080-8_10
Meng, X., Yan, T., Jiang, Z., & Lyu, Y. (2025) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac63849.2025.11132703 · Cited by 2
“To address these challenges, various privacy-preserving methodologies have been proposed for machine learning tasks, including differential privacy [1], secure multi-party computation [2], federated learning [3], and trusted execution environments [4].”
Xiong, M., Wang, Y., & Olya, H. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-80262-963-720251009 · Cited by 1
Enhancing Breast Cancer Detection Through Explainable Federated Learning Models
Pasha, A., Rahman, S. Z., Ahamed, S. S., Kumar, D. N. P., & Manjunatha, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-00715-5_28 · Cited by 1
Kumar, G. S., Devi, G. S., Sajid, P. M., Jyostna, K., Sangeetha, V., Gorikapudi, S., Alam, T., & Prabhakaran, T. (2025) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.12327
“To implement differential privacy in AI/ML workflows, the Laplace mechanism is used, which adds Laplacian noise to the model gradients during training [21].”
Integrating AI and Neuroscience for Cyber Threat Detection and Response
Shaikh, A., Aparna, V. B., & Dogra, S. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5012-7.ch004
Homomorphic MaxPooling via Bootstrapping for Privacy-Preserving Neural Networks
Zhang, P., Lu, H., & Ding, T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6209-1_1 · Cited by 1
Artificial Intelligence startups and financial conditions: Evidence from Italy
Giaretta, E., & Zen, F. (2026) · Finance research letters · doi:10.1016/j.frl.2026.109584 · Cited by 2
Rethinking Query Choices for Differential Privacy Auditing
Deng, Z., Chen, H., Jiang, S., Ma, W., Wen, S., Zhu, T., & Xiang, Y. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3658692
Self-citationArtificial Intelligence Breakthroughs and Data Futures: A Retrospective and Prospective Review
Yuksel, B. B., & Metin, A. Y. (2026) · Academic Platform Journal of Engineering and Smart Systems · doi:10.21541/apjess.1705042 · Cited by 5
Differentially Private Fine-Tuned BERT for Sensitive Entity Recognition
Satyavathi, G., & Vatsavayi, V. K. (2025) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn67655.2025.11368231
“To address these problems, researchers have suggested various privacy-preserving methods, e.g., differential privacy (DP), federated learning, and secure multiparty computation (SMC) [7], [8].”
Differentially Private Mechanisms Using Enhanced Direction-Oriented Smooth Sensitivity
Yamamoto, A., & Shibuya, T. (2026) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc67433.2026.11393770
“[16], [28], including data management [2] and medical data analysis [14].”
46722 AI Bias and Fairness: Unveiling Solutions for Ethical Algorithmic Practices
Tiwari, A., & Sharma, N. (2026) · De Gruyter eBooks · doi:10.1515/9783112214374-022
Far, S. B., Qazani, M. R. C., & Rad, A. I. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11567-w · Cited by 1
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.