The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
A Robust Privacy-Preserving Federated Learning Model Against Model Poisoning Attacks
Abstract
Although federated learning offers a level of privacy by aggregating user data without direct access, it remains inherently vulnerable to various attacks, including poisoning attacks where malicious actors submit gradients that reduce model accuracy. In addressing model poisoning attacks, existing defense strategies primarily concentrate on detecting suspicious local gradients over plaintext. However, detecting non-independent and identically distributed encrypted gradients poses significant challenges for existing methods. Moreover, tackling computational complexity and communication overhead becomes crucial in privacy-preserving federated learning, particularly in the context of encrypted gradients. To address these concerns, we propose a robust privacy-preserving federated learning model resilient against model poisoning attacks without sacrificing accuracy. Our approach introduces an internal auditor that evaluates encrypted gradient similarity and distribution to differentiate between benign and malicious gradients, employing a Gaussian Mixture Model and Mahalanobis Distance for byzantine-tolerant aggregation. The proposed model utilizes Additive Homomorphic Encryption to ensure confidentiality while minimizing computational and communication overhead. Our model demonstrates superior performance in accuracy and privacy compared to existing strategies and encryption techniques, such as Fully Homomorphic Encryption and Two-Trapdoor Homomorphic Encryption. The proposed model effectively addresses the challenge of detecting maliciously encrypted non-independent and identically distributed gradients with low computational and communication overhead.
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
“Another promising technique is robust aggregation methods, where model updates are evaluated for anomalies before being integrated into the global model [72,73].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [72]
In the citing paper
“Defense techniques such as adversarial training, where the model is pre-trained with adversarial samples, have displayed promise.”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [72]
In the citing paper
“In targeted poisoning attacks, malicious contributors corrupt the model to misidentify specific data, which could be utilized to target certain diseases or demographic groups.”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [72]
In the citing paper
“Designed to prevent malicious model updates from impacting the global model, this technique uses statistical approaches to filter irregularities in model updates, maintaining robustness even with a certain degree of compromised participants [72].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [72]
In the citing paper
“Data manipulation attacks are crucial threats in FL, particularly in healthcare.”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [72]
In the citing paper
“Untargeted poisoning, in contrast, aims to degrade model efficiency globally, risking patient results over the board [72,76].”
From Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration (2024) · cites this paper as [72]
Citations
Cites
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
SecureML: A System for Scalable Privacy-Preserving Machine Learning
Mohassel, P., & Zhang, Y. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.12 · Cited by 1,936
On the Convergence of FedAvg on Non-IID Data
Li, X., Huang, K., Yang, W., Wang, S., & Zhang, Z. (2019) · arXiv · doi:10.48550/arxiv.1907.02189 · Cited by 1,575
FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping
Cao, X., Fang, M., Liu, J., & Gong, N. Z. (2021) · Proceedings 2021 Network and Distributed System Security Symposium · doi:10.14722/ndss.2021.24434 · Cited by 999
Data Poisoning Attacks Against Federated Learning Systems
Tolpegin, V., Truex, S., Gursoy, M. E., & Liu, L. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58951-6_24 · Cited by 927
Verifynet: Secure and verifiable federated learning
Xu, G., Li, H., Liu, S., Yang, K., & Lin, X. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2929409 · Cited by 839
Personalized Cross-Silo Federated Learning on Non-IID Data
Huang, Y., Chu, L., Zhou, Z., Wang, L., Liu, J., Pei, J., & Zhang, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i9.16960 · Cited by 749
ShieldFL: Mitigating Model Poisoning Attacks in Privacy-Preserving Federated Learning
Ma, Z., Ma, J., Miao, Y., Li, Y., & Deng, R. H. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3169918 · Cited by 371
Privacy-Enhanced Federated Learning Against Poisoning Adversaries
Liu, X., Li, H., Xu, G., Chen, Z., Huang, X., & Lu, R. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3108434 · Cited by 351 · cited 8×
“Model poisoning adversaries manipulate user input by submitting poisonous updates to local models to create arbitrary deviance from correct trends [3].”
BackgroundMethodInfluentialPrivacy-Preserving Collaborative Deep Learning With Unreliable Participants
Zhao, L., Wang, Q., Zou, Q., Zhang, Y., & Chen, Y. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2939713 · Cited by 215
Research works printed but not linked: 12
- Bhagoji, Analyzing federated learning through an adversarial lens, 634
- Fung, The limitations of federated learning in Sybil settings, 301
- Fang, Local model poisoning attacks to Byzantine-robust federated learning, 1623
- Mozaffari, Every vote counts: Ranking-based training of federated learning to resist poisoning attacks, 1721
- Blanchard, Machine learning with adversaries: Byzantine tolerant gradient descent, 30, 118
- El Mhamdi, The hidden vulnerability of distributed learning in Byzantium, 3521
- Xie, DBA: Distributed backdoor attacks against federated learning
- Bell, ACORN: Input validation for secure aggregation, 4805
- Shen, AUROR: Defending against poisoning attacks in collaborative deep learning systems, 508
- 2023, Availability With Redundancy
- Goodfellow, 2016, Deep Learning
- 2016, Paillier Cryptosystem
Cited by
Sorted by citations
Items 101–200 of 380
Cheng, H., Qiang, C., Cong, L., Xiao, J., Liu, S., Zhou, X., Wang, H., Ruan, M., & Lv, C. (2025) · Applied Sciences · doi:10.3390/app15031261 · Cited by 5
Federated Learning for Privacy-Preserving: Current Status and Future Directions
Chouhan, A., & Yao, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6403-0_7 · Cited by 6
-, R. K., Shieh, C., Chakrabarti, P., Kumar, A., Moolchandani, J., & Sinha, R. (2025) · EPJ Web of Conferences · doi:10.1051/epjconf/202532801066 · Cited by 7
Huang, H. M., Xiao, D., Wang, M., Liang, J., Li, M., Chen, L., & Liu, Y. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111043 · Cited by 4
Lv, J., Kim, B., & Li, K. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3624693 · Cited by 4
“However, federated learning systems remain vulnerable to security threats, as highlighted by Yazdinejad et al. [22], who developed robust privacy-preserving approaches against model poisoning attacks using encrypted gradient evaluation and byzantine-tolerant aggregation.”
Badar, H. M. S., Kajla, N. I., Mahmood, K., Khan, M. W., Fan, G., & Zhang, C. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3644701 · Cited by 4
“Recent encrypted-similarity schemes [18] improve tolerance but add cryptographic overhead.”
Govindarajan, V., Ahmed, F., Kamaluddin, K., Mushtaq, Z., Alshammari, K., & Khan, F. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-025-01117-7 · Cited by 4
“Yazdinejad et al. [26] proposed a robust privacy-preserving federated learning framework that mitigates model poisoning attacks while maintaining high accuracy and scalability across distributed nodes.”
Blockchain-enabled defenses in federated learning: A comprehensive survey
Dib, O. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100932 · Cited by 4
Graph intelligence for IoT and CPS security: From connectivity patterns to cyber-physical reasoning
Ahmad, H. B., Gao, H., & Latif, N. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100978 · Cited by 4
Model Recovery in Federated Unlearning With Restricted Server Data Resources
Zhang, J., Zhao, M., Wang, Z., Su, W., & Wang, P. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3540463 · Cited by 7
“Yazdinejad et al. [23] used an internal auditor to assess encrypted gradients, combine Gaussian mixture models and Mahalanobis distance for Byzantine fault-tolerant aggregation, and apply additive homomorphic encryption to reduce computational and communication overhead.”
A Federated Learning Network Intrusion Detection System for Multiple Imbalances
Zeng, Y., Zheng, P., & Li, J. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889171 · Cited by 5
Privacy-preserving and efficient verifiable federated learning scheme based on proxy re-signature
Niu, S., Zhou, X., Wang, N., Kong, W., & Chen, L. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128422 · Cited by 5
Ỹe, Z., Zhang, S., Wen, Z., Wu, L., Cai, T., Zhang, M., Wang, M., Zhang, J., & Lei, M. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114419 · Cited by 4
zkFL: Verifiable Byzantine-Robust Federated Learning Against Malicious Servers
Tang, X., Li, M., Zhang, T., Lin, Y., Zhu, L., Zhou, C., & Liu, X. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3622060 · Cited by 4
“Typical attacks include sign-flipping [54], scaling [55], and Gaussian noise injection [56], which create substantial deviations from benign updates while preserving plausible gradient structures to evade simple detection.”
Liu, W., Cui, W., Wang, B., Pan, H., She, W., & Zhao, T. Q. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111179 · Cited by 4
Nair, D. G., Narayana, C. V. A., Reddy, K. J., & Nair, J. J. (2025) · IEEE Access · doi:10.1109/access.2025.3563544 · Cited by 4
“Robust PPFL [35] integrates Paillier encryption like methods to defend against model poisoning attacks.”
Munnangi, A. K., Maruthapillai, K., Rajeyyagari, S., Sekaran, R., Ravi, V., & Mazroa, A. A. (2025) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-01982-1 · Cited by 4
“A robust privacy-preserving federated learning model was introduced in [33] with lesser computational cost.”
Improving Adversarial Robustness via Decoupled Visual Representation Masking
Liu, D., Chen, T., Peng, C., Wang, N., Hu, R., & Gao, X. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3577966 · Cited by 4
“(e-mail: gaoxb@cqupt.edu.cn). utilized generated adversarial examples as data augmentation during model training, and the model can learn the characteristics of adversarial examples and enhance its robustness.”
R-SFLLM: Jamming Resilient Framework for Split Federated Learning With Large Language Models
Djuhera, A., Andrei, V. C., Li, X., Mönich, U. J., Boche, H., & Saad, W. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3594107 · Cited by 5
“Much research has focused on addressing these challenges via adversarial AI training methods [5] and model-based solutions [6], and in [7], the authors closely investigated such attack and defense strategies, particularly in 6G networks, exposing critical vulnerabilities across all network layers.”
Cheng, Y., Hu, Y., Liu, W., & Bilal, M. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122100 · Cited by 3
XSShield: Defending Against Stored XSS Attacks Using LLM-Based Semantic Understanding
Zhou, Y. W., Wang, E., Yang, W., Ge, W., Yang, S., Zhang, Y., Qu, W., & Xie, W. (2025) · Applied Sciences · doi:10.3390/app15063348 · Cited by 4
FedMVA: Enhancing software vulnerability assessment via federated multimodal learning
Liu, Q., Ju, X., Chen, X., & Gong, L. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112469 · Cited by 3
A lightweight Federated Learning-based Intrusion detection model for Internet of Things
Tariq, N., Humayun, M., Alwakid, G. N., Almas, B., Jhanjhi, N. Z., & Zakwan, M. (2024) · International Multi-Topic Conference · doi:10.1109/inmic64792.2024.11004389 · Cited by 3
“It reduces power consumption and bandwidth consumption, reduces transmission delay, and facilitates data confidentiality as only the updated model [10], [11].”
Secure and scalable IoT healthcare with a permissioned blockchain and encryption techniques
Yahyaoui, A., Kotel, S., Hamel, L., Lahouij, A., & Kamoun, R. M. (2025) · Computing · doi:10.1007/s00607-025-01523-x · Cited by 4
“Yazdinejad et al. [27] introduced a robust privacy preserving federated learning model against model poisoning attacks.”
Ren, P., Yang, B., Wang, T., Zhou, Y., & Zhu, F. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103522 · Cited by 3
Can Differential Privacy Hinder Poisoning Attack Detection in Federated Learning?
Aggarwal, C., Nair, D. G., Mohammadi, J. A., Nair, J. J., & Ott, J. (2025) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan14040083 · Cited by 3
“The recent paper [27] utilizes additive homomorphic encryption to ensure confidentiality while minimizing computational and communication overhead.”
Correlation-Aware Multi-Similarity Learning for Federated Human Activity Recognition
Ju, J., Cai, H., Zhou, T., Sheng, B., Zhou, J., Fan, W., & Xiao, F. (2025) · International Workshop on Quality of Service · doi:10.1109/iwqos65803.2025.11143429 · Cited by 4
“Federated Learning (FL) has emerged as a promising distributed learning paradigm to address the above privacy concerns [2]–[4].”
FedPillarNet: Unifying personalized and global features for federated 3D LiDAR object detection
Li, B., Ren, S., Zhao, S., Cui, M., & Huang, K. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103584 · Cited by 3
Thuong, D. B., Duc, M. V., An, V. T., Thanh, N. H., Tran, K. P., & Hương, T. T. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130237 · Cited by 3
Tang, Y., Ni, L., Zhang, J., & Liang, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130455 · Cited by 3
Murala, D. K., Ahmad, S., Ponnapalli, V. A. S., Vuyyuru, V. A., & Hitimana, E. (2025) · Scientific Reports · doi:10.1038/s41598-025-27077-8 · Cited by 3
“Blockchain creates decentralised trust and protection against tampering, while machine learning allows computers to learn and adapt to find insider risks in real time 4,19 .”
BlockIntelChain: a blockchain-based cyber threat intelligence sharing architecture
Tolah, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-29152-6 · Cited by 3
“Yazdinejad et al. 32 and Ullah et al. 33,34 presented blockchain-federated learning models that detect cyberattacks while mitigating poisoning risks in IoT and vehicular systems.”
Dolatshah, K., Haghighat, A. T., Khajehvand, V., & Shirvani, M. H. (2026) · Computing · doi:10.1007/s00607-025-01593-x · Cited by 3
“In federated learning, each agent trains the model with its own data, which can enhance privacy [21,[ 22 ].”
Robust federated learning for cloud environments using evolutionary optimization and blockchain
Panimalar, S. P., & Gunasundari, S. (2026) · Scientific Reports · doi:10.1038/s41598-025-34290-y · Cited by 3
Zhang, Y., Wang, L., Li, M., Gai, K., & Wang, J. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3654756 · Cited by 3
“However, due to its decentralized and open nature, FL is susceptible to multifaceted privacy and security challenges [17], [18], [19], [20], [21], [22], [23], [24], [25], [26] that require innovative solutions and robust frameworks.”
Two-Dimensional Privacy-Preserving Federated Learning Scheme Against Poisoning Attacks
Gu, K., Zhao, W., Tan, J., Yang, Z., Li, X., & Weijia Jia, B. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3656703 · Cited by 3
Melhem, A., AlEroud, A. F., Al-Mamun, A., & Ibrahem, M. I. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3658441 · Cited by 4
“The work in [17] introduces a defense mechanism based on Gaussian mixture models and Mahalanobis distance for detecting model poisoning, combined with additive HE (AHE) to ensure data confidentiality.”
Designing resilient IoT and Edge Computing with federated tinyML
Laiu, P., Li, M., Nichols, J. A., Huettel, M., Sikkema, I., & Mathur, M. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103709 · Cited by 3
Integrating Trustworthiness Into the AI Lifecycle (Trustworthiness)
Lingam, R. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-6935-8.ch008 · Cited by 3
A blockchain-driven intrusion detection model for secure communication in IoT-WSN mesh architectures
Elumalai, G., Kumar, J. A., Sivakumar, P., & Teresa, V. V. (2026) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-026-02195-w · Cited by 3
Valdez, W., Parra-Ullauri, J. M., Simeonidou, D. E., & Kertész, A. (2026) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2026.104510 · Cited by 3
Rekha, M., & S.Senthilkumar (2026) · Iranian Journal of Science and Technology Transactions of Electrical Engineering · doi:10.1007/s40998-026-01120-4 · Cited by 3
Fed-HA: A Privacy-Preserving Robust Federated Learning Scheme based on Homomorphic Assessment
Xu, W., Xu, X., & Wang, H. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104144 · Cited by 4
ESFLM: Efficient and Secure Federated Learning Model with Homomorphic Encryption
Li, Y., Xia, C., Li, C., Li, X., & Wang, T. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.104118 · Cited by 3
Venčkauskas, A., Toldinas, J., Morkevičius, N., Serkovas, E., & Krištaponis, M. (2025) · Electronics · doi:10.3390/electronics14061215 · Cited by 4
SecFedDNN: A Secure Federated Deep Learning Framework for Edge–Cloud Environments
Alamir, R. H., Noor, A., Almukhalfi, H. M., Almukhlifi, R., & Noor, T. H. (2025) · Systems · doi:10.3390/systems13060463 · Cited by 4
Qiao, Y., Le, H. Q., Raha, A. D., Tran, P.-N., Adhikary, A., Zhang, M., Nguyen, L. X., Huh, E., Niyato, D. T., & Hong, C. S. (2025) · doi:10.36227/techrxiv.174762883.35612385/v1 · Cited by 3
Chesterman, S. A., & Loy, H. C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6046274 · Cited by 4
Leveraging local and global relationships for corrupted label detection
Lam, P., Nguyen, H.-L., Dang, X.-T. D., Tran, V.-S., Le, M.-D., Nguyen, T.-T., Nguyen, S., & Vo, H. D. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.107729 · Cited by 2
Alsalamah, S., Alnehmi, S. A., Abanumai, A. A., Alnashri, A. H., Alduhim, S. S., Alnamlah, N. A., Alghamdi, K., Sheerah, H. A., Alsalamah, S. A., & Alsalamah, H. A. (2025) · Electronics · doi:10.3390/electronics14132527 · Cited by 2
Adaptive IoT architecture with incremental learning for on-line solar production forecasting
Fiore, G. D., Montanaro, T., Sergi, I., & Patrono, L. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101724 · Cited by 2
Quantum-Resilient Federated Learning for Secure and Scalable Cyber-Physical Systems
Prajwalasimha, S. N., Saini, D. K. J. B., Shelke, N. M., Pimpalkar, A. P., Kumar, G. H., & Chirchi, V. (2025) · International Conference on Soft Computing for Security Applications (ICSCSA) · doi:10.1109/icscsa66339.2025.11170994 · Cited by 2
“The use of ZKPs [28] and trust aware aggregation [29] enabled strong global model updates.”
FedMPC: Metropolis criterion based aggregation method for federated learning
Cui, J. T., Li, Y., Guo, H., Heng, L., & Liu, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131756 · Cited by 2
Gao, K., Zhu, T., Ye, D., Liu, B., & Zhou, W. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3630811 · Cited by 2
“These attacks are particularly challenging because they exploit the assumption that most clients are honest, causing the global model to diverge or perform poorly [34].”
Lightweight ECC-Based Self-Healing Federated Learning Framework for Secure IIoT Networks
Salim, M. M., Naaz, F., & Choi, K. (2025) · Sensors · doi:10.3390/s25226867 · Cited by 2
“Some works claim that blockchain and incentives alone secure FL participation [17,18]; others stress cryptography or trusted hardware as decisive [19,20]; and still others rely solely on robust aggregation [21,22].”
Luo, W., Fang, Q., & Kang, W. (2025) · Symmetry · doi:10.3390/sym17111977 · Cited by 2
“Second, adversarial robustness is insufficient, as malicious clients may upload abnormal gradients that compromise the integrity of the global model [16].”
DamPa: Dynamic Adaptive Model Poisoning Attack in Federated Learning
Hu, F., Zhang, A., Liu, X., & Li, M. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3631449 · Cited by 2
“[11].”
Qi, T., Xue, L., Zhan, Y., & Ma, X. (2025) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3719027.3744805 · Cited by 2
Rodríguez-Barroso, N., García-Márquez, M., Luzón, M. V., & Herrera, F. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104236 · Cited by 5
Zhao, X. H., & Arebi, P. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01338-9 · Cited by 2
“Yazdinejad proposed privacy-preserving federated models against poisoning [34].”
Differential Privacy-Based Adaptive Sparse Federated Learning in UAV Networks
Chen, Z., Du, J., Jiang, C., Hou, X., Han, Z., & Poor, H. V. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3644438 · Cited by 2
“This approach provides significant advantages in privacy protection because it allows individual devices to train models locally while sharing only model updates instead of their raw sensitive data [26], [27], [28].”
Federated deep convolutional neural network architecture for renal cancer classification
Yu, X., Lin, Z., Zhou, C., Wang, H., & Wang, M. (2025) · Discover Computing · doi:10.1007/s10791-025-09870-1 · Cited by 2
“Under the Feder-ated Learning framework, models can be trained locally on decentralized data, sharing only model parameters rather than raw data, thus ensuring data privacy and compliance [7].”
Gan, C., Tan, X., Zhu, Q., Saini, A., Jain, D. K., & Diro, A. A. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104348 · Cited by 2
Task-Oriented Network Reliability for Federated Learning-Enabled Industrial Internet of Things
Zheng, D., Fu, X., Pace, P., Aloi, G., & Fortino, G. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3646666 · Cited by 2
“Threats like data contamination [12], [20], model poisoning attacks [21], [22], and gradient inversion attacks [22], [23] occur frequently, making the construction of a robust security protection system a key requirement to ensure the stable operation of FL-enabled IIoT systems.”
Enhancing security in IoMT using federated TinyGAN for lightweight and accurate malware detection
Durga, S., Shankar, M. G., Daniel, E., & Varghese, B. G. (2026) · Scientific Reports · doi:10.1038/s41598-026-37830-2 · Cited by 2
Yang, C., Zhou, Z., Liang, Y., & Tang, C. (2026) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2026.3665733 · Cited by 2
“Another study [31] combines additive homomorphic Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
A privacy-preserving multi-user retrieval system for multimodal artificial intelligence
Gao, Y., Luo, W., Wang, C., Ahmad, N. S., Wang, X., & Goh, P. (2026) · Scientific Reports · doi:10.1038/s41598-026-40734-w · Cited by 4
Graph-based federated learning for smart healthcare: A comprehensive survey
Huda, S. M. A., Canzaniello, M., Annunziata, D., & Piccialli, F. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108524 · Cited by 2
Wang, J., Tang, L., Jiang, W., Li, H., Yi, X., Dong, Z., & Chau, K. W. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104723 · Cited by 2
Defending federated learning-based intrusion detection systems against model poisoning attacks
Zukaib, U., Cui, X., Niaz, F., Liang, D., Zheng, C., & Din, S. U. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134208 · Cited by 2
Alotaibi, N. S. (2024) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-024-01799-4 · Cited by 2
“%) and minimal resource consumption (5.13%), highlighting its superior efficiency and effectiveness in intrusion detection for cloud environments compared with existing models, like [24–30] respectively.”
InfluentialHan, C., Yang, T., Cui, Z., & Sun, X. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3521329 · Cited by 2
“Current security mechanisms tend to focus on centralized data processing, lacking targeted measures for edge computing environments [8].”
Wang, L., Pang, S., Zhao, Z., He, X., Zhang, K., Gui, H., & Wang, N. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113921 · Cited by 2
Privacy preserving hierarchical federated learning approach for secure urban mobility prediction
Naresh, V. S., & Ayaaappa, D. (2025) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-02053-1 · Cited by 2
“Yazdinejad et al. [ 17 ] designed a framework which could identify model poisoning attacks efficiently while consuming the mini - mum computational resources.”
Efficient federated learning via aggregation of base models
Wang, P., Zhong, Z., & Wang, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0327883 · Cited by 2
SpyShield: a Spyfall inspired defense mechanism against poisoning attacks in federated learning
Elgharieb, Y., Alexan, W., El-Aasser, M., & Ghantous, M. M. (2025) · Scientific Reports · doi:10.1038/s41598-025-16158-3 · Cited by 2
Zhang, H., Yu, Z., Wang, G., Xu, F., Zhang, Y., Hu, C., Wang, X., & Yu, J. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3620529 · Cited by 2
“Topreventpoisoningattackswithoutcompromising privacy,existingsolutions[20],[21],[22],[23]adopt HomomorphicEncryption(HE)toanalyzetheencrypted modelupdates.”
Rahman, M. S., Elmahallawy, M., Madria, S., & Frimpong, S. (2025) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass66014.2025.00061 · Cited by 2
“Among the three risks to FL in mines—untargeted attacks, targeted attacks, and unreliable mines–the targeted attack is easier to detect through parameter pattern analysis [12, 13].”
Patel, D., & Avadia, S. A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5360240 · Cited by 2
Liang, P., Chen, J., Yu, H., Huang, H., & Pu, B. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5383089 · Cited by 2
Yan, J., Li, Y., Yin, S., Kang, X., Wang, J., Zhang, H., & Hu, B. (2024) · Electronics · doi:10.3390/electronics13173548 · Cited by 2
Tan, Q., Li, Y., & Shin, B. (2025) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2025.063811 · Cited by 6
“Other notable strategies include model poisoning attacks [20], which amplifies the impact of malicious updates by scaling the gradients, and label-flipping attacks [21], where attackers alter the labels of local datasets to manipulate the global model.”
A privacy-enhancing and lightweight framework for device-free localization-based AIoT system
Wang, H., Zhang, C., Zhao, L., Huang, H., & Su, C. (2025) · Computer Communications · doi:10.1016/j.comcom.2025.108200 · Cited by 1
Hussein, S., Yuan, J., Shen, Z., & Eldow, M. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3569657 · Cited by 1
“We note the increasing literature incorporating HE in FL systems to tackle these adversarial robustness issues [33], [34], [35], [36].”
Yan, Q., Wang, G., Zhu, D., & Li, J. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425520135 · Cited by 1
Whiskey: Large-Scale Identification of Mobile Mini-App Session Key Leakage With LLMs
Chen, Y., Chen, Y., Wang, R., Wang, T., Ji, S., Shan, H., Xu, D., & Pan, Z. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3575561 · Cited by 1
“Yazdinejad et al. [45], [46] employed homomorphic encryption and Trusted Execution Environments (TEE) to protect against sensitive data leakage, thereby ensuring key security.”
Federated Learning for Secure and Resilient AI Systems
Farooqi, S. A. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-2200-1.ch010 · Cited by 1
Priya, N. H. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70153 · Cited by 1
HEaaN-ID3: Fully Homomorphic Privacy-Preserving ID3-Decision Trees Using CKKS
Lee, D., Shin, H., Choi, J., & Lee, Y. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.064161 · Cited by 1
“Additionally, homomorphic encryption (HE)-based machine learning algorithms have garnered significant attention owing to the growing importance of privacy-preserving machine learning [2–6].”
PrivRS: Differentially private synthetic data generation via role similarity
Ye, X., Zhu, Y., Pan, J., Zhang, M., & Deng, H. (2025) · Computers & Security · doi:10.1016/j.cose.2025.104616 · Cited by 1
A survey of deep learning for face presentation attack detection
Sheikhfathollahi, M., Parkinson, S., Hill, R., & Khan, S. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131136 · Cited by 1
Knowledge Driven Signal Transformer for Emitter Recognition
Ren, S., Yang, S., Zhan, M., Qi, Z., & Feng, Z. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3586503 · Cited by 1
“In addition, in real-world electromagnetic environments, the received signals can be highly disturbed and degraded [58], [59].”
Enhancing long-term memory in federated class continual learning with lightweight adapters
Wang, P., Ji, W., Zhong, Z., Bao, W., Zhang, Y., & Chen, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131459 · Cited by 1
Deception-Based Defense of Poisoning Attack in Federated Learning
Masse, G. C. T., Benslimane, A., Tchendji, V. K., & Hemida, A. H. A. (2025) · IEEE Access · doi:10.1109/access.2025.3611806 · Cited by 1
“These differences, often measurable through statistical techniques such as Euclidean distance [25], cosine similarity [11], and Pearson correlation coefficient [13], enable the distinction and grouping of models based on their malignancy or benignity.”
A dual-aggregation approach to fortify federated learning against poisoning attacks in IoTs
Dalaien, M. N. A., Ullah, R., & Al-Haija, Q. S. A. (2025) · Array · doi:10.1016/j.array.2025.100520 · Cited by 1
A Comparative Analysis of Label Flipping and Backdoor Data Poisoning Attacks in Federated Learning
Bisna, N. D., Navaneeth, D., & James, A. (2025) · International Conference on Soft Computing for Security Applications (ICSCSA) · doi:10.1109/icscsa66339.2025.11171343 · Cited by 1
DRIFT: DCT-based robust and intelligent federated learning with trusted privacy
Dong, Q., Bai, Y., Su, M., Gao, Y., & Fu, A. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131697 · Cited by 1
Biadgligne, Y., Baghoussi, Y., Li, K., & Jorge, A. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02725-2_3 · Cited by 1
DynFed: Adaptive Federated Learning via Quantization-Aware Knowledge Distillation
He, N., Chen, Y., Jiang, Z., Yang, S., & Sun, L. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755451 · Cited by 1
“This imbalance can lead to issues such as client dropout during training, affecting overall training efficiency and model quality [42].”
An Integrated Approach to Mitigate Poisoning Attacks in Federated Learning Frameworks
Latif, S., Djenouri, D., & Adamatzky, A. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228082 · Cited by 1
Metadata
- Authors
- Yazdinejad, A., Dehghantanha, A., Karimipour, H., Srivastava, G., & Parizi, R. M.
- Affiliations
- University of Guelph (CA)
- University of Calgary (CA)
- Brandon University (CA)
- Kennesaw State University (US)
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2024
- Volume
- 19
- Pages
- 6693-6708
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W4400076000
- Cited by
- 380
- References
- 30
- Citations by year
- 2026: 139 · 2025: 205 · 2024: 33
- FWCI
- 55.64
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Keywords
- privacy-preserving federated learning, model poisoning, additive homomorphic encryption, Gaussian mixture model, Mahalanobis distance, communication overhead
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
