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 301–380 of 380
Security and Privacy Challenges in AI-Driven IoT Big Data Analytics
Kumar, R., & Sharma, H. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7046-0.ch005
Yang, G., Guo, S., Xiao, Y., Mao, X., Huang, S., Qi, F., & Hao, J. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3675692
“Early research primarily tracked the gradient norm or the downward trend of the loss function [61], [62], while subsequent works introduced curvature and flatness metrics to characterize the stability of the optimization process [63].”
RAHAS: Reliable, Privacy-Aware Human Activity Sensing
Aryendu, I., & Wang, Y. (2026) · ACM Transactions on Computing for Healthcare · doi:10.1145/3803414
“Alternatively, FL was designed to protect data privacy by decentralizing training while keeping data locally, thereby improving privacy and efficiency [39, 57].”
FedAligns: A Federated Learning-Based IoT Intrusion Detection Method With Direction-Aligned Updates
Qiu, K., Xu, Z., Lu, J., Xu, X., Zhao, S., Yan, M., Luo, T., Yang, D., & Li, Z. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3679719
“Facing increasingly complex adversarial environments, recent literature has explored multidimensional defense strategies [34], [35], [36], [37], [46].”
Zhao, H.-J., Lu, J., Jiang, Y., & Lu, X. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133615
Temporal Conditional Score Network for Multivariate Time Series Anomaly Detection
Hao, Z., Xu, W., Zhang, X., Yazidi, A., & Yu, K. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3681780
“The robustness is further improved [20] by designing a Byzantine-tolerant aggregation strategy with low computational and communication overhead.”
Chang, R.-I., Lu, W.-X., & Yang, C. (2026) · Electronics · doi:10.3390/electronics15081658
ELTFL: A Trusted Heterogeneous Federated Learning in Edge Scenario
Lai, J., Wang, R., Luo, C., & Zhang, F. (2026) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010264
Sparsity-Induced Reparametrization for Differentially Private Federated Learning
Lai, J., Zhang, F., Li, D., Zhang, F., Wang, R., & Zhang, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463812
ROPFL: Robust and Privacy-Preserving Decentralized Federated Learning Framework
Li, K., Yang, X., Ban, Z., Qi, S., He, Z., Zhao, H., & Wang, Q. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465073
D-LoRA: A Dual Low-Rank Adaptation Framework for Cost-Efficient Personalized Federated Learning
Gu, H., Li, J., Peng, M., Zhang, X., Ma, Y., & Huang, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461534
Deshmukh, S. A., & Kasar, S. L. (2026) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70414
Chuang, Y., & Zhang, Q.-X. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114734
Privacy-Aware Synthetic Tabular Data Generation for Healthcare: Application to Sepsis Detection
Macias-Fassio, E., Morales, A., Pruenza, C., Fiérrez, J., & Espósito, C. (2026) · Bioengineering · doi:10.3390/bioengineering13050511
“Future work will further extend this analysis by incorporating complementary privacy evaluation methods, including adversarial attacks and differential privacy-based approaches [75,76].”
FedKSS: One-shot federated learning with kernel space statistics
Ding, J., Jiang, L., Jia, L., Fu, X., & Jiang, Y. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104443
Xu, H., Wu, J., Wu, H., Chen, J., Xiao, M., & Zhang, T. (2026) · Applied Artificial Intelligence · doi:10.1080/08839514.2026.2663618
S-LARF: Layered Adversarial Resilience Framework for spaceborne anomaly detection
Belali, F., Essetty, A., & Bah, S. (2026) · International Journal of Critical Infrastructure Protection · doi:10.1016/j.ijcip.2026.100851
Miloudi, A., Laouid, A., Bounceur, A., Bouhamed, M. M., & Hammoudeh, M. (2025) · International Conference on Future Networks and Distributed Systems (ICFNDS) · doi:10.1145/3789692.3789788
“Privacy-Preserving Defenses : Frameworks like ShieldFL and PEFL integrate privacy-preserving encryption techniques (e.g., homomorphic encryption, secure aggregation) with model poisoning defenses, maintaining effectiveness even in heterogeneous data environments [13, 30, 33].”
Efficient privacy-preserving federated learning with local differential privacy
Yin, C., & Zeng, Q. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112351
Subramanian, R. S., Lydia, A., Aswini, J., & Kothandapani, S. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01302-2
“In Yazdinejad et al., [57] have developed robust, privacy-preserving federated learning frameworks that maintain high accuracy while defending against model poisoning attacks.”
A comprehensive survey on privacy-preserving recommender system in pervasive environments
Ouhiba, I. B., Kodia, Z., & Azzouna, N. B. (2026) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-026-00235-1 · Cited by 1
Enhancing Privacy and Accountability in Federated Learning for Smart IoT
Lian, Z., Zeng, Q., & Su, C. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-23883-2_36
A Privacy-Preserving Step-Size Collection Against Poisoning Attacks for Federated Learning in IoT
Song, J., Wang, J., Guan, X., & Hu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-20080-8_2
Li, Z., Cao, C., Yu, H., Wang, M., Yan, H., & Sun, J. (2025) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait67930.2025.11522078
Deep learning with optimization for social media fake profile detection
Goyal, B., Gill, N. S., Gulia, P., Alduaiji, N., Shukla, P. K., Shukla, P. K., & Vishnoi, S. (2026) · Social Network Analysis and Mining · doi:10.1007/s13278-026-01586-4
“This will render such communication less confidential and violate information security [ 12, 13, 14].”
Sankeawthong, S., Cao, X., Zhao, S., & Zhang, Y. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112430
Beyond accuracy: Convergence degradation under pixel-level perturbations in federated learning
Chen, A., Manzoor, H. U., Rais, R. N. B., Hussain, S., Mohjazi, L., & Zoha, A. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134212
“However, many of these studies focus on large update deviations, backdoor behaviour, or direct model poisoning [35,41,42].”
Edge intelligence and collaborative learning in 6G networks
Bezziane, M. B., Zitouni, F., Kafi, M. R., Benguenane, M., Khaldi, Y., & Zga, A. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-340570-9.00017-2
Yao, S., Chen, Y., Li, J., & Li, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6915146
A Blockchain-based Framework for CTI Sharing in Healthcare
Poodi, V. V. D., & Nazma, S. (2026) · International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV) · doi:10.1109/icicv68925.2026.11554819
“Moreover, the proposed method will provide privacy as with the federated learning-based privacy models [19], the proposed approach guarantees privacy by using hash-based anonymization and managed data access, which is more appropriate in a healthcare system that is regulatory-compliant.”
Resilience of federated learning: perspectives on attacks and defenses
Raj, P. V. P., Gupta, A., & Das, S. K. (2026) · Elsevier eBooks · doi:10.1016/b978-0-44-344433-3.00016-2
Kavitha, C. R., & Sowmya, K. N. (2026) · Cybernetics and Information Technologies · doi:10.2478/cait-2026-0012
WCFL: Robust and Resource-Efficient Federated Learning Using Model Weight Caching
Sinha, A. K., Priyambada, S., Mishra, R., & Gupta, H. P. (2026) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc65185.2026.11555617
“Similarly, Yazdinejad et al. [12] combined homomorphic encryption with Byzantine-tolerant aggregation to strengthen security, but the cryptographic overhead limits scalability.”
Bilateral-verifiable and robust secure aggregation via TEE for asynchronous federated learning
Liu, W., Zhang, Y., Wu, A., Cao, J. P., Wang, Y., & Tian, Y. (2026) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2026.104542
BRPPFL: A Byzantine-Robust and Privacy-Preserving Framework for Cloud–Edge Federated Learning
Zhang, L., Qiancheng, Y., Wuwei, Y., & He, L. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112498
Tanhaei, M. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100935
A comprehensive survey on communication optimization and privacy preservation in federated learning
Kunjumon, A., Sarath, G., & Nair, J. J. (2026) · Discover Computing · doi:10.1007/s10791-026-10272-0 · Cited by 1
Poster Abstract: Auditor-Free Byzantine-Resilient Federated Learning Via Functional Inner Products
Gurve, M. K., Gupta, D., Nitin, & Prasad, Y. (2026) · ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems - Posters and Demos (SenSys-Adjunct) · doi:10.1109/sensys-adjunct71932.2026.00096
“Existing defenses rely on robust aggregation rules, statistical filtering, or auditor-based [1] architectures that evaluate gradient consistency prior to aggregation.”
InfluentialDivergence-Based Adaptive Aggregation for Byzantine Robust Federated Learning
Xiao, B., Zhu, F., Zhang, J., Ni, W., & Wang, X. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3707437 · Cited by 2
“These attacks, commonly known as Byzantine attacks [4], [5], disrupt the global model training by tampering with the local data or model updates of the attacked workers, which seriously deteriorate training performance and system security.”
Alsadhan, N. A., Ullah, I., Haider, Z. A., Khan, F. M., & Ullah, I. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112514
Less is More: Persistent Low-Frequency Backdoor Injection in Federated Learning
Ye, P., Li, Y., He, K., Wang, H., Du, R., & Wang, W. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571624
Qazi, A., Jadoon, A. A. K., & Arshad, S. (2026) · Scientific Reports · doi:10.1038/s41598-026-60574-y
FedTLA: Trust‐Differentiated Selective Aggregation for Backdoor‐Resilient Federated Learning
Li, H., Tang, Q., & Wang, Y. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70820
“Recent variants further improve robustness via dimension-wise rate con-trol, representation-level decoupling, robust loss design, or poisoning-robust FL mechanisms [ 24 – 27].”
Poisoning-Resilient Decentralized Federated Learning via Hierarchical Credibility Consensus
Hua, Y., Lyu, X., Ren, C., Hou, Y., Chen, Q., Cui, Q., & Tao, X. (2026) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc69287.2026.11579832
Su, T., Liu, P., Li, C., Peng, K., Peng, H., & Yao, Y. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581562
“Federated Learning (FL) [1], [2] is a distributed machine learning approach that enables multiple participants (such as different devices or organizations) to collaboratively train a shared machine learning model while preserving data privacy and security [3].”
Integrating IoBNT and AI-Enabled Digital Twins in E-Health and Biotechnology
Jamshidi, M. B., Hoang, D. T., Nguyen, D. N., Niyato, D. T., & Warkiani, M. E. (2025) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps68340.2025.11590963
“When combined with FL, this synergy enables the framework to harness the advanced image processing capabilities of CNNs while ensuring privacy and scalability, critical features for handling distributed medical data [11].”
A Secure and Resilient Framework for Wildfire Management via UAVs and Blockchain Federated Learning
Lamani, L., Leka, E., Rexha, G., & Aliti, A. (2026) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro70003.2026.11591814
“Addressing these attacks requires additional defense mechanisms, such as robust aggregation and anomaly detection techniques [21], [23].”
Secure and Scalable Federated Learning with Dynamic Trust Scoring and Anomaly-Resilient Aggregation
Jha, T., & Bhargavi, M. S. (2025) · IEEE International Conference on Innovate for Humanitarian: Tech Solutions for Global Challenge (ICIH) · doi:10.1109/icih67754.2025.11609041
“Finally, Yazdinejad et al. [14] present a robust privacy-preserving FL model against model poisoning attacks, reinforcing the defense narrative by integrating strategies that complement the robustness and privacy pillars outlined by Tariq et Despite advances in trustworthy federated learning,…”
Sun, Z., Gao, W., Yin, P., Li, W., Zhang, M., Chen, Y., Shu, J., & Guo, Y. (2026) · Computer Standards & Interfaces · doi:10.1016/j.csi.2026.104189
Medshield a privacy enhanced threat detection framework for secure industrial IoT healthcare
Murala, D. K., Madhura, K., Gopi, D. A., Balagoni, Y., & Romeo, B. M. (2026) · Discover Internet of Things · doi:10.1007/s43926-026-00443-2
“…absence of edge-deployable, lightweight machine learning models that achieve a balance between efficiency and accuracy for real-time threat detection in contexts with limited resources [32, 33] MedShield and show its strong privacy protection, quick response times, and excellent detection accuracy.”
Zhang, L., Zhu, N., He, J., & Jurcut, A. D. (2026) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs69761.2026.11613520
“…vectors have been identified,including membership inference attacks that determine whether specific data points were part of the training set [6], property inference attacks that reveal statistical properties of the data distribution [7], and data reconstruction attacks that can partially or…”
Liu, Y., Yu, C., Zheng, Z., Li, W., & Song, J. L. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3712025
MONZA: A Score System for Malicious Clients Detection
Veiga, R., Morais, R., Bastos, L., Sargento, S., do Rosário, D. L., & Cerqueira, E. (2026) · Journal of Internet Services and Applications · doi:10.5753/jisa.2026.7098
Poison-Resilient and Privacy-Preserving Federated Learning Scheme in Mobile Systems
Zhao, Q., Gu, C. G. C., Jiang, B., Zhou, Y., & Jing, Z. (2026) · Mobile Networks and Applications · doi:10.1007/s11036-026-02504-w
“Entities in federated learning [3] consist of CS and a set of participants, which include devices, organizations, or individuals that possess private datasets.”
A Verifiable Accountable Anonymous Authentication Interface for Cross-Silo Federated Learning
Wang, Z. (2026) · IEEE Access · doi:10.1109/access.2026.3721480
Dubey, P., & Kumar, M. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116817
XFedRec: a Robust, Adaptive, and Explainable Federated Recommendation Framework
Ravichandran, K., & Poravi, G. (2026) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai69603.2026.11641955
“Standard Federated Averaging (FedAvg) is provably vulnerable to local model poisoning and Byzantine attacks [5].”
Alamer, A. M. A., & Basudan, S. (2026) · Information Sciences · doi:10.1016/j.ins.2026.124044
Kavitha, L. (2026) · International Conference on Emerging VLSI and Semiconductor Technology for AI and Computing Applications (EVST) · doi:10.1109/evst69093.2026.11660530
“Improving the robustness of model aggregation is therefore critical for secure Federated Learning-based intrusion detection [6], [8], [9] Recent studies have investigated feature selection, adaptive aggregation, personalized federated learning, and deep learning techniques to improve FL-based…”
A Secure Federated Learning and Blockchain Framework for E-Health Threat Detection
Banupriya, P. G., & K.Vanitha (2026) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-026-02702-6
“Moreover, the Byzantine Fault Tolerance (BFT) mechanism that works together with Proof of Stake (PoS) increases the reliability and robustness of the consensus process [5, 6].”
A comprehensive survey on robust federated learning: From threat models to defense mechanisms
Fu, X., Yan, H., Zhou, D., Zeng, S., & Li, F. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.101041
Rahman, M. M., Mamun, Q., Bewong, M., & Islam, M. Z. (2026) · IEEE International Conference on Edge Computing and Communications (EDGE) · doi:10.1109/edge72783.2026.00028
“A malicious participant can still upload poisoned updates that distort the global model, manipulate downstream decisions, or inject targeted behaviour [8].”
Gu, C., Zhu, K., Hu, D., & Liu, Z. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104731
Basak, S., & Chatterjee, K. (2026) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2026.104612
Fu, X., Li, J., Zhong, H., Wang, D., Chen, W., & Li, F. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.101049
Vanajakshi, J., Renuka, A., Kamath, V. P., & Adesh, N. D. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.101056
Kavitha, T., & Manimala, S. V. R. (2026) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2026.105360
Secure Federated Learning: A Privacy-Preserving Approach to Collaborative Model Training
Krishnaiah, K. R., Bharathi, P., Rajeswari, P. V. N., Manjunath, B. E., Battula, B. P., & Sathish, K. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-25620-1_25
Feng, L., Zhou, J., Fang, F., Yu, Y., & Wang, J. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112773
Embedding-Based Anomaly Detection for Poisoned Client Filtering in Federated Learning
Dhillon, H., & Singh, B. C. (2026) · IEEE International Conference on Intelligence and Security Informatics (ISI) · doi:10.1109/isi69914.2026.11685841
“In model poisoning [9], adversaries directly manipulate transmitted weight updates, potentially scaling them to dominate FedAvg aggregation.”
Nikam, S., & Kulkarni, N. (2026) · Research Square · doi:10.21203/rs.3.rs-10799357/v1
A systematic review of federated learning applications in mitigating insider threats
Mdaghri, A. A., Alae, A., & Hilali, A. A. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116478
Privacy‐Preserving Federated Deep Learning for 6G Network Security Monitoring
Kanimozhi, J. K., Shiny, M. I., Senthilkumar, A., & Joshi, S. (2026) · International Journal of Communication Systems · doi:10.1002/dac.70609
“The robust federated learning against model poisoning (RFLP) model was created to counteract model poisoning, and so it enhances resilience and integrity in adversarial conditions [17].”
Federated Unlearning in Agentic Energy Systems: Security and Governance Implications
Yazdinejad, A., Niazi, M., Kong, J. D., & Nathwani, J. S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-41864-7_28
Self-citationFedTGR: Topology-Guided Byzantine-Resilient Federated Learning for Massive AI Agents
Qiao, Z., Zhang, Y., Cao, M., Pan, Y. C., Liu, J., Chen, D. W., & Cao, B. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3742774
“Others combine robustness with privacy by encrypting gradients or using secure multi-party protocols, thereby limiting adversarial opportunities to tamper with raw updates [30], [31], [32].”
Kothavle, P. S., & Chandre, P. R. (2026) · International Conference on Computer, Mechatronics, Robotics & Artificial Intelligence (ICCMRAI) · doi:10.1109/iccmrai67732.2026.11724306
Yao, S., Chen, Y., Li, J., & Li, S. (2026) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2026.109852
TAFL: Trust-Aware Federated Learning for Anomalous Client Detection, Isolation, and Recovery
Rashid, M. M., Uddin, M. P., Xiang, Y., Sood, K., Zhang, Y., & Gao, L. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3744607
“Blockchain and audit-oriented approaches support traceability and incentive enforcement [34], [35], [36], yet typically do not couple auditability with uncertainty-aware trust, dynamic isolation, and recovery.”
Kardam, K., Khan, T., & Kaushik, V. (2026) · International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI) · doi:10.1109/icoici69824.2026.11723680
“The IDS is an essential parameter to manage the network traffic for detecting malicious activities in the network [5] [6].”
Blockchain-Enhanced IoT Framework for Secure Environmental Data Integrity
Balaram, A., Padmanaban, K., Prasad, R. G., & Anupama, J. (2026) · Journal of Computer Information Systems · doi:10.1080/08874417.2026.2731441
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
