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 201–300 of 380
Sankaran, M., Sataar, Z., Siddhanti, P. N., Ghosh, S., & Narendran., S. (2025) · International Conference on Intelligent Communication Networks and Computational Techniques (ICICNCT) · doi:10.1109/icicnct66124.2025.11232609 · Cited by 1
“Therefore, this affects the data aggregation reliability, and all users have limited control over how their data have been handled by data consumers [5].”
Defense Against Poisoning Attacks on Federated Learning With Neighborhood Coulomb Force
Wang, B., Tian, Y., Guo, Y., & Li, H. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3637669 · Cited by 1
Efficient lightweight privacy data anomaly detection solution with robust aggregation
Zhao, J., Wen, B., Yang, J., & Zhou, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-30180-5 · Cited by 1
“…and edge-level weights to facilitate high-accuracy semi-supervised training 28 , while Yazdinejad et al. employ Gaussian mixture models and Mahalanobis-distance based assessments on encrypted gradients to attain Byzantine-tolerant aggregation with favorable privacy–accuracy trade-offs 29 .”
Zhong, L., Zeng, J., Wang, Z., Tang, H., & Wen, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130652 · Cited by 1
Privacy-Preserving Cross-Client Recommender Systems With Fully-Separable Graph Neural Networks
Zhang, Y., Zhao, W., & Hu, C. (2025) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2025.3645737 · Cited by 1
“However, existing privacy-preserving schemes [9], [10], [11], [12] are mostly limited to single-dimensional data protection.”
Secure federated learning based on multi-round critical parameters
Zhang, Z., Ma, C., Huang, B., Li, G., Niu, Z., & Qiu, D. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132471 · Cited by 1
Multimodal Feature Fusion Against Poisoning Attacks in Federated Graph Learning
Mu, S., Lu, N., Shi, W., Kumari, S., Agarwal, K., & Alsabaan, M. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3599182 · Cited by 1
“Based on the attack target, model poisoning attacks can be divided into two main categories: Adversarial Mode (Convergence Inhibition): Attackers inject random noise into local updates to reduce the accuracy of the global model [5], [25].”
Federated Learning for Phishing Detection and Protection in Wearable Health Networks
Rahaman, M., Vanna, K., Gaurav, A., Berutu, S. S., Nedjah, N., Chui, K. T., & Gupta, B. B. (2025) · International Symposium on Communications and Information Technologies · doi:10.1109/iscit67082.2025.11231737 · Cited by 1
“Besides these benefits, FL presents additional challenges: communication overheads, the non-IID (non-independent and identically distributed) data distribution among the clients, and novel threats such as model poisoning and reconstruction attacks [18].”
Peng, C., & Xian, H. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.104345 · Cited by 2
Resource-Efficient joint clustering and storage optimization for blockchain-Based IoT systems
Peng, K., Hu, X., Hu, J., Yao, Z., Deng, T., Hu, M., Cai, C., & Xiong, Z. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108354 · Cited by 2
Guo, H., Chen, W., Li, J., & Geng, X. (2026) · Scientific Reports · doi:10.1038/s41598-026-35420-w · Cited by 1
“To address this problem, Yazdinejad et al. 3 proposed a secure aggregation protocol that guarantees gradient privacy.”
Lokesh, R. S. (2026) · Iran Journal of Computer Science · doi:10.1007/s42044-025-00353-6 · Cited by 1
Bermperis, A. I., Memos, V. A., Stergiou, C. L., Plageras, A. P., & Psannis, K. E. (2026) · Applied Sciences · doi:10.3390/app16020835 · Cited by 1
Belal, M. M., Saleti, S., & Elakkiya, E. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-025-01011-7 · Cited by 1
A survey on AI-empowered task-oriented sensing, communication, and computation in 6G networks
Zhang, Y., Wang, X., Luo, X., Pei, X., Li, F., Han, D., & Li, T. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.100899 · Cited by 3
Ramírez-Gordillo, T., Pujol, F. A., & Mora, H. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.132828 · Cited by 1
A Robust Privacy-Preserving Federated Learning Method Against Poisoning Attacks on Non-IID Data
Fang, C., Chang, D., Li, Y., Yang, F., Liu, Y., & Ma, B. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3658384 · Cited by 1
“However, the substantial computational cost incurred by homomorphic encryption remains a major challenge that the above works [16], [35], [36] must overcome.”
Privacy-Preserving and Poisoning-Resilient Enhanced Cross-Silo Federated Learning
Zheng, X., Yan, X., Yang, F., Ng, W. W. Y., Li, Y., & Wu, S. (2025) · International Conference on Blockchain Technology and Information Security (ICBCTIS) · doi:10.1109/icbctis66509.2025.11387244 · Cited by 1
“To mitigate the impact of poisoning attacks, many solutions have been presented [11, 17, 18].”
A Weighted Asynchronous Federated Learning Scheme to Combat Model Poisoning Attacks
Wang, J., Tang, Y., Cheng, H., & Song, J. (2025) · International Conference on Blockchain Technology and Information Security (ICBCTIS) · doi:10.1109/icbctis66509.2025.11387697 · Cited by 1
“Although these approaches advance robustness and privacy preservation, most still rely on synchronous assumptions, static defense thresholds, or high communication overhead, limiting their practicality in dynamic asynchronous environments [16].”
Game-Theoretic Defense Against Encrypted Data Poisoning in Federated Learning for Social Networks
Sun, Z., Gao, W., Yin, P., Li, W., Zhang, M., Chen, Y., & Shu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7027-0_6 · Cited by 1
A review of security threats and privacy issues in federated learning
Agrahari, A. K., Dinker, A. G., & Singh, R. B. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01067-z · Cited by 3
Ebrahimi, M., Sahay, R., Akram, B., & Hosseinalipour, S. (2026) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2026.1792429 · Cited by 1
“To mitigate poisoning attacks, robust model aggregation mechanisms, such as Byzantine-resilient methods (e.g., trimmed mean and Krum), can be employed to reduce the in fl uence of anomalous or malicious updates (78).”
Bakar, R. A., Paolucci, F., Cugini, F., Olmos, J. J. V., & Marinis, L. D. (2025) · Globecom · doi:10.1109/globecom59602.2025.11431830 · Cited by 1
Effective Dual-Layer Poison Attacks Detection in Privacy-preserving Federated Learning
Zhang, X., Chi, H., Li, Y., Jiang, S., Du, X., & Hughes, D. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432262 · Cited by 1
“1) Performance Under Different Poison Attacks: We define no detection method as the baseline and also compare it with well-known algorithms, including krum [16] and RPPFL [6].”
Defending federated learning against adversarial attacks: A systematic literature review
Babar, F. F., Khan, S., & Parkinson, S. (2026) · Cyber Security and Applications · doi:10.1016/j.csa.2026.100127 · Cited by 1
Reinforcement learning based security method for IoT-Edge computing
Kumar, A., & Singh, D. (2026) · Wireless Networks · doi:10.1007/s11276-026-04123-5 · Cited by 1
“In IoT data security, PDR, Average throughput, and E2E delay are not just performance metrics, they are behavioral signals that tell the agent whether its security decisions are helping or hurting the network [ 36–38 ].”
FedHAP: Federated hierarchical adaptive prompt learning for cross-domain generalization
Zhang, C., Zhang, J., Xie, Y., Mao, W., Wang, X., Zhou, B., & Yu, B. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115193 · Cited by 1
Zhu, L., Zhao, B., & Peng, R. (2026) · Electronics · doi:10.3390/electronics15081572 · Cited by 1
“(2) Mitigating Byzantine Faults: REM protects against Byzantine faults, which include malicious behaviors like data poisoning [84,85] and model poisoning [86,87].”
Qiu, X., Lv, M., Zhu, T., Song, Q., & Chen, T. (2026) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2026.104457 · Cited by 1
Muthupandian, S., & Kumar, D. M. (2026) · Scientific Reports · doi:10.1038/s41598-026-48650-9 · Cited by 1
FLEX: Robust client selection for dynamic federated learning environments
Mao, L., Li, H., Lin, W., Lin, W., Zhang, L., & Wang, J. Z. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116014 · Cited by 1
Hu, F., Zhang, A., Li, M., & Wang, C. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3689720 · Cited by 1
“More concerning, state-of-the-art robust aggregation techniques [9], [11], [16], [17] collapse entirely under Byzantine majority scenarios, where malicious clients can collectively orchestrate their updates to manipulate the aggregation process while appearing individually legitimate.”
Privacy preserved federated deep learning for disease classification of patients medical images
Dachepalli, V., & Gavini, S. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115512 · Cited by 1
The shift from centralized analytics to federated learning in smart grids: a comprehensive review
Sultana, A., & Sarma, K. K. (2026) · Knowledge and Information Systems · doi:10.1007/s10115-026-02793-3 · Cited by 1
A Byzantine-Robust Secure Federated Learning Scheme in Heterogeneous Data
Wang, R., Wang, R., Li, Z., Zhang, F., Li, J., & Li, X. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3714122 · Cited by 1
“In light of these concerns, Secure Federated Learning (SFL) [6], [7], [8], [9], [10], [11] has emerged as a promising paradigm to address privacy vulnerabilities.”
InfluentialRobust Federated Learning Under Realistic Corruption: An Iterative Filtering Approach
Wu, J., Zhao, P., Wang, C., & Liu, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3523293 · Cited by 1
“However, with the growing size of modern distributed systems, due to transmission error, system malfunctioning, and malicious attacks, some clients may send wrong gradients to the server [1], [3], [4], [5], [6], [7], [8], [9].”
Client dependability evaluation in federated learning framework
Han, K., Zhang, G., Yang, L., & Bai, J. L. (2025) · doi:10.1117/12.3058096 · Cited by 1
“Federated learning (FL) is a widely adopted distributed machine learning paradigm that emphasizes enhanced privacy protections [1][2][3].”
FSLBSC: Knowledge-Driven Federated Learning for Unbalanced Labeling AIS Signal Identification
Tian, Q., Wang, S., & Wang, M. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3600757 · Cited by 2
“Integrating DA with FL can not only preserve the benefits of FL in terms of distributed privacy protection and low communication expenses [27] but also alleviate the influence of cross-node data distribution disparities on model performance via the DA mechanism [28].”
Li, H., & Li, Z. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5358246 · Cited by 1
Patel, P., & Shah, D. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5363844 · Cited by 1
Privacy of Deep Learning Systems: A Penetration Testing FrameworkPreprint
Vayghan, B. J. (2024) · doi:10.36227/techrxiv.172296728.87985494/v1
A Confidential Batch Payment Scheme with Integrated Auditing for Enhanced Data Trading Security
Wang, Z., Zhong, L., Zhao, L., Wang, Y., & Zhu, Z. (2024) · Electronics · doi:10.3390/electronics13163278
Improving Heart Disease Risk Assessment with Advanced Deep Learning and Federated Learning
Simha, A., & Prasad, S. K. (2024) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit2410458
PIM-FFL: Evaluating Participation Index Metrics for Fairness Enhancement in Federated Learning
Batool, H., Xu, J., Rehman, A. U., Kaur, G., & Bharany, S. (2024) · International Conference on Sustainable Expert Systems (ICSES) · doi:10.1109/icses63445.2024.10763231
“In a separate approach [18] developed Refiner.”
Cho, C., Youn, T.-Y., Kim, B., & Cho, H. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.056952 · Cited by 1
“An alternative to traditional block cipher modes is homomorphic encryption [26–29], which allows operations like addition and multiplication to be performed on encrypted data.”
DLShield: A Defense Approach Against Dirty Label Attacks in Heterogeneous Federated Learning
Sameera, K. M., Abhinav, M., Amal, P. P., Abhiram, T., Abishek, R. K., Amal, T., Anaina, P., Vinod, P., A., R. R. K., & Conti, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-80408-3_9
Assessing the Impact of Dynamic Backdoor Attacks on Federated Learning Models
Raj, P. V. P., & Gupta, A. (2024) · International Conference on Computational Intelligence and Network Systems (CINS) · doi:10.1109/cins63881.2024.10864408
“Even though collaborative learning enables effective usage of data while maintaining user and data privacy, the inherent anonymity of FL also unlocks the door for adversaries to influence and manipulate the global model [3].”
Distributional Black-Box Model Inversion Attack With Multi-Agent Reinforcement Learning
Bao, H., Wei, K., Wu, Y., Qian, J., & Deng, R. H. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3564043
“Furthermore, defense strategies from federated learning [38] may further strengthen model resilience.”
Bendhi, M. R. (2025) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei65986.2025.11013674
“Yazdinejad et al. [5] proposed a privacy-preserving federated learning (PPFL) model using an internal auditor using Gaussian Mixture Models (GMM) and Mahalanobis Distance (MD) for detecting malicious gradients.”
On Defending against Label Flipping Poisoning Attack for Personalized Federated Learning
Chen, Y., Hung, H.-N., Yang, S., Chou, Y.-C., & Lin, P. (2025) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc65282.2025.11059648
Dao, B. T., Duc, V. V., Vu, T. A., Nguyen, H. T., Tran, K. P., & Truong, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5362071
Gunathilaka, D. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5357675
A Comparative Evaluation of Secure Email Protocols: PGP vs. S/MIMEPreprint
Ghanta, K. S., & Gottipati, N. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5358848
Huynh, T. M. Q., & Chen, W. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5357830
A Comparative Analysis of Traditional and Machine Learning-Based Cryptanalytic ApproachesPreprint
Shah, D. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5358781
Securing Forensic Data with Cryptographic TechniquesPreprint
Rai, N., & Haque, M. F. U. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5368369
Efficient Privacy-Preserving Federated Learning for Consumer Electronics Using Proxy Re-Encryption
Zhang, J., & Shi, C. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3596793
“To address these vulnerabilities, lightweight secure aggregation protocols [19], [23], [24], [25], [26], [31], [32], [33], [34] have been devised.”
Kusi, A., & Asoma, D. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5370817
Shishir, M. A. K. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5359442
A Review and Comparative Analysis of Password Hashing Techniques: Evaluating Bcrypt and Argon2Preprint
Etese, O., & Adesina, A.-A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5366362
A Review of Lightweight Multi-Party Computation and Federated Learning in Financial SystemsPreprint
Thomas, T. T., & Shukla, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5363411
Kusi, A., & Asoma, D. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5363403
Review on Cryptographic Techniques for Privacy-Preserving Data Sharing in CloudPreprint
Makadia, J., & Patel, P. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5363399
Jakhu, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5363395
A Comparative Systematic Review of PRESENT and SIMON Algorithms for IoT DevicesPreprint
Patel, V., & Prajapati, K. H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5359440
Mitigating AI security threats: Why the G7 should embrace ‘federated learning’
Yazdinejad, A., & Kong, J. D. (2025) · doi:10.64628/aam.9hgaukrha
Self-citationA federated learning privacy preserving scheme for infrastructure-less vehicular networks
Luo, X., Chen, X., Ma, Y., Cheng, Q., & Chen, X. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0219
Re‐Sampling Calibrated SNN Loss: A Robust Approach to Non‐ IID Data in Federated Learning
Kang, N., & Im, J. (2025) · Expert Systems · doi:10.1111/exsy.70145
Achieving consistency in FedSAM using local adaptive distillation on sports image classification
Zhen, K., wu, J., Park, J., Shao, R., Zhang, X., & Yu, S. (2025) · PLoS ONE · doi:10.1371/journal.pone.0333210
“Due to its data availability without visibility property, FL has been widely applied across various domains, including healthcare, finance, and transportation [6–14].”
A Dropout-Resilient and Privacy-Preserving Framework for Federated Learning via Lightweight Masking
Jiang, Y., Liu, J., Xu, C., Zuo, C., Xu, L., & Lei, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3543-9_16
Wang, X., Li, S., Fan, F., Wang, S., Li, Y., & Zheng, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3543-9_22
Enhanced security verifiable secure aggregation scheme in federated learning
Yao, W., Han, Y., Zhou, T., & Wang, X. (2025) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-025-02111-8
“Here, we do not consider the situation where users directly forge or tamper with their own model parameters and upload error gradients to the server to mislead the aggregation results, such as data poisoning attacks [ 21].”
Secure federated learning with configurable reliability in heterogeneous edge computing
Liu, Y., Liang, Y., Zhang, R., & Zhou, Z. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111808
RKU: Relevant Knowledge-aware Unlearning for Federated Continual Learning
Zhang, H., Yang, L., & Jiang, Z. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11210106
“For security, the FCL system is potentially vulnerable to model poisoning [10] or data poisoning [11] attacks, and MU can remove the negative effects of these attacks on the model.”
Adaptive Federated Distillation for Multi-Domain Non-IID Textual Data
Xiao, J., & Liu, J. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228583
“Federated learning has garnered significant interest in natu-ral language processing tasks [4], [17]–[22] due to its potential for collaborative training on distributed data while maintaining data privacy [3], [23].”
FLgym: Toward Robust and Byzantine-Resilient Federated Learning
Xiao, K., Wang, Q., & Anagnostopoulos, C. B. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3643162 · Cited by 1
“These attacks are characterised by their stealthiness and destructive potential, often rendering conventional anomaly detection techniques ine ff ective [13].”
Jiang, W., Yongjian, L., Gao, Q., Xu, H., & Wang, H. (2025) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2025.104328
Byzantine-Resilient Federated Computation of Differentially Private Summary Statistics
Segalini, G., Fernandes, M., & Decouchant, J. (2025) · International Middleware Conference · doi:10.1145/3721462.3770766
“In the last decade, methods have been described to improve privacy guarantees [78] or accuracy [63] of federated computations.”
AdaptiveShield: Dynamic Defense Against Decentralized Federated Learning Poisoning Attacks
Feng, Y., Zheng, B., Li, T., Wu, C., Ma, Z., Shen, Y., & Ma, J. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3641896
“Abbas et al. [37] combined byzantine-tolerant aggregation with homomorphic encryption to safeguard encrypted models against poisoning attacks.”
Secure and Robust Federated Learning Under Dual-Server Architecture in Internet of Things
Liu, S., Ren, J., Meng, R., Yan, X., Miao, Y., Liu, Z., Peng, J., Zou, Y., Wang, Z., Li, H., et al. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3647441
“Therefore, the study of defenses against poisoning attacks within PPFL has attracted increasing attention in recent years [13], [14], [15].”
Tang, J., Li, Z., Huang, H., Yu, L., Xiao, F., & Deng, R. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3648113
Evaluating Model Resilience to Data Poisoning Attacks: A Comparative Study
Udoidiok, I., Li, F., & Zhang, J. (2025) · Information · doi:10.3390/info17010009
“Prior research suggests regularization offers moderate resistance against label-flipping attacks and noisy data distributions [25].”
Roy, S., Singha, S. K., & Bera, D. (2025) · IEEE Access · doi:10.1109/access.2025.3648434
“An improved solution [27] is proposed using additive homomorphic encryption and a similarity-based auditor to increase accuracy and reduce computational complexity; however, the inherent computational overhead remains high.”
Secure Rational Delegation Federated Learning
Li, M., Tian, Y., Zhang, J., Yang, Z., Xiong, J., & Ma, J. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3650379
“Federated learning (FL) [2], [3], an emerging paradigm in distributed machine learning, enables cross-device modeling by utilizing local training and exchanging model parameters to break down data silos [4].”
Crowdsensing with Federated Trust Management: Adaptive Defense Against Malicious Contributions
Xu, J., Zhang, C., Jin, L., & Su, C. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-3480-7_12
Zhao, L., Qin, S., Shi, Y., Li, W., Gao, F., & Jin, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6029577
Fu, Y., Xia, M., Weng, L., & Lin, H. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3655382
“…employ two technical paradigms: 1) systematically optimized DP parameter configurations, exemplified by adaptive budget allocation [9] and multitiered noise injection mechanisms [10] and 2) hybrid privacy frameworks integrating secure multi-party computation and homomorphic encryption [11].”
Chen, J., Xu, X., Xiang, H., Fu, S., & Bilal, M. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3654994
“Attack-ers submit some malicious updates to impair the performance of the model [11].”
PFL-SA: Personalized federated learning with switchable aggregation strategy
Jia, W., Ren, C., & Cheng, S. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343527
“…been widely adopted by researchers across numerous domains for diverse studies, such as decentration (e.g., [4] and [5]), individuation (e.g., [6] and [7]), privacy (e.g., [8] and [9]), etc. Never-theless, a significant challenge in federated learning is the constraint on communication resources.”
Privacy-Preserving Federated Learning With Blockchain Auditing for Consumer Electronics Applications
Kumar, A., Chatterjee, K., Singh, A. P., Kumar, A., & Aldawsari, H. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3657426
Inversion, Membership, and Poisoning Attacks in Federated Learning - Challenges and Defenses
Farooqi, S. A., Rahman, A. A., & Saad, A. B. (2026) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom69009.2026.11360927
“• Model Poisoning: Attackers directly manipulate model updates, often scaling or altering gradients, to shift the global model’s decision boundar y [31].”
Liu, J., Yang, J. J., Xia, X., Zuo, C., Xu, L., Qu, Y., & Huang, X. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3659330
“To combat model poisoning attacks without compromising accuracy, Yazdinejad et al. [30] developed a robust privacy-preserving FL model using additive HE.”
Najafi, M., Alavizadeh, H., Shahraki, A. S., Kayes, A. S. M., & Rahayu, W. J. (2025) · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · doi:10.1109/raid67961.2025.00017
“As a result, there is often a trade-off between privacy and performance, while improving accuracy generally requires relaxed privacy constraints [33], [34], [35].”
Qi, Q., Lei, Y., Li, Y., Li, H., & Zhou, Q. F. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3661499
“Secondly, current decentralized FL architectures are susceptible to Byzantine attacks [6], [7], [8], [9], where malicious participants can send arbitrary or conflicting information to disrupt the sys-tem.”
Practical and Flexible Backdoor Attack Against Deep Learning Models via Shell Code Injection
Wang, J., Liu, H., Tao, R., Sun, J., Liu, X., & Zhao, Y. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3662587
“Generally, existing backdoor attack methods could be categorized into di ff erent types, i.e. , the poisoning-based [28], [29] and non-poisoning-based backdoor attacks [30], [31].”
Kuang, J., Bian, X., Feng, S., Pei, S., Liu, Z., Lan, R., & Pan, X. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113338
Architectural Models and Security Considerations for Federated Learning
Patil, R. Y., Patil, Y. H., & Özer, Ö. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-6224-3.ch003
Jia, J., Liu, Z., Jia, A., Feng, J., & Feng, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133222
Khan, A. A., Almansour, H., Alghuried, A., Alsayaydeh, J. A. J., Mohamed, M. A., & Ullah, S. (2026) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-026-00879-5
Sun, X., Shi, L., Wei, L., He, M., & Lian, H. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432772
“Gaussian attack [25] is a model poisoning attack, in which the attacker does not modify the local data but creates malicious updates by adding Gaussian noise to the locally computed gradient.”
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
