SCA: Sybil-Based Collusion Attacks of IIoT Data Poisoning in Federated Learning
Abstract
With the massive amounts of data generated by industrial Internet of Things (IIoT) devices at all moments, federated learning (FL) enables these distributed distrusted devices to collaborate to build machine learning model while maintaining data privacy. However, malicious participants still launch malicious attacks against the security vulnerabilities during model aggregation. This article is the first to propose Sybil-based collusion attacks (SCA) in the IIoT-FL system for the vulnerabilities mentioned above. The malicious participants use label flipping attacks to complete local poisoning training. Meanwhile, they can virtualize multiple Sybil nodes to make the local poisoning models aggregated with the greatest possibility during aggregation. They focus on making the joint model misclassify the selected attack class samples during the testing phase, while other nonattack classes kept the main task accuracy similar to the nonpoisoned state. Exhaustive experimental analysis demonstrates that our SCA has a superior performance on multiple aspects than the state-of-the-art.
Integrity signals
Registry
Cites
Statistics
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?
The ASR of label-flipping attacks can be increased when the attacker controls more compromised clients.
“Some studies have shown that the attack success rate (ASR) of label-flipping attacks can be increased when the attacker controls more compromised clients [233], [234].”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [234]
Cites
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,890 · see citing works
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · see citing works
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322 · see citing works
Federated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210 · see citing works
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108 · see citing works
Federated Learning in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565 · see citing works
Nasr, M., Shokri, R., & Houmansadr, A. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00065 · Cited by 1,760 · see citing works
How to backdoor federated learning
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2018) · arXiv · doi:10.48550/arxiv.1807.00459 · Cited by 1,495 · see citing works
A survey on security and privacy of federated learning
Mothukuri, V., Parizi, R. M., Pouriyeh, S., Huang, Y., Dehghantanha, A., & Srivastava, G. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.10.007 · Cited by 1,480 · see citing works
A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective
Roh, Y., Heo, G., & Whang, S. E. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2946162 · Cited by 980 · see citing works
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 · see citing works
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
Fang, M., Cao, X., Jia, J., & Gong, N. Z. (2019) · arXiv · doi:10.48550/arxiv.1911.11815 · Cited by 828 · see citing works
Estimating a Dirichlet Distribution
Minka, T. P. (2000) · Cited by 758 · see citing works
Model Pruning Enables Efficient Federated Learning on Edge Devices
Jiang, Y., Wang, S., Valls, V., Ko, B. J., Lee, W., Leung, K. K., & Tassiulas, L. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3166101 · Cited by 594 · see citing works
DBA: Distributed Backdoor Attacks against Federated Learning
Xie, C., Huang, K., Chen, P., & Li, B. (2020) · International Conference on Learning Representations · Cited by 468 · see citing works
Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues
Du, Z., Wu, C., Yoshinaga, T., Yau, K.-L. A., Ji, Y., & Li, J. (2020) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2020.2992630 · Cited by 393 · see citing works
Mitigating Sybils in Federated Learning Poisoning
Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2018) · arXiv · doi:10.48550/arxiv.1808.04866 · Cited by 385 · see citing works
Jia, B., Zhang, X., Liu, J., Zhang, Y., Huang, K., & Liang, Y. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3085960 · Cited by 351 · see citing works
Can You Really Backdoor Federated Learning?
Sun, Z., Kairouz, P., Suresh, A. T., & McMahan, H. B. (2019) · arXiv · doi:10.48550/arxiv.1911.07963 · Cited by 348 · see citing works
A Blockchained Federated Learning Framework for Cognitive Computing in Industry 4.0 Networks
Qu, Y., Pokhrel, S. R., Garg, S., Gao, L., & Xiang, Y. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3007817 · Cited by 341 · see citing works
Dynamic-Fusion-Based Federated Learning for COVID-19 Detection
Zhang, W., Zhou, T., Lu, Q., Wang, X., Zhu, C., Sun, H., Wang, Z., Lo, S. K., & Wang, F.-Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3056185 · Cited by 329 · see citing works
Fusion of Federated Learning and Industrial Internet of Things: A survey
Boobalan, P., Ramu, S. P., Pham, Q., Dev, K., Pandya, S., Maddikunta, P. K. R., Gadekallu, T. R., & Huynh‐The, T. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109048 · Cited by 321 · see citing works
Understanding Distributed Poisoning Attack in Federated Learning
Cao, D., Chang, S., Lin, Z., Liu, G., & Sun, D. (2019) · 2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads47876.2019.00042 · Cited by 285 · see citing works
The Limitations of Federated Learning in Sybil Settings
Fung, C., Yoon, C. J. M., & Beschastnikh, I. (2020) · Recent Advances in Intrusion Detection · Cited by 265 · see citing works
Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoT
Zhang, P., Wang, C., Jiang, C., & Han, Z. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3064351 · Cited by 238 · see citing works
Fed-IIoT: A Robust Federated Malware Detection Architecture in Industrial IoT
Taheri, R., Shojafar, M., Alazab, M., & Tafazolli, R. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3043458 · Cited by 218 · see citing works
Federated Learning for Industrial Internet of Things in Future Industries
Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., Niyato, D., & Poor, H. V. (2021) · IEEE Wireless Communications · doi:10.1109/mwc.001.2100102 · Cited by 166 · see citing works
TrustFed: A Framework for Fair and Trustworthy Cross-Device Federated Learning in IIoT
Rehman, M. H. U., Dirir, A. M., Salah, K., Damiani, E., & Svetinovic, D. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3075706 · Cited by 132 · see citing works
Mitigating Poisoning Attacks on Machine Learning Models: A Data Provenance Based Approach
Baracaldo, N., Chen, B., Ludwig, H., & Safavi, J. A. (2017) · Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security · doi:10.1145/3128572.3140450 · Cited by 108 · see citing works
Analytical Model for Sybil Attack Phases in Internet of Things
Mishra, A. K., Tripathy, A. K., Puthal, D., & Yang, L. T. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2843769 · Cited by 96 · see citing works
IOTFLA : A Secured and Privacy-Preserving Smart Home Architecture Implementing Federated Learning
Aivodji, U. M., Gambs, S., & Martin, A. (2019) · 2019 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2019.00041 · Cited by 93 · see citing works
FDA$^3$: Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications
Song, Y., Liu, T., Wei, T., Wang, X., Tao, Z., & Chen, M. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3005969 · Cited by 66 · see citing works
Liu, Y., Zhao, R., Kang, J., Yassine, A., Niyato, D. T., & Peng, J. (2021) · ACM Transactions on Internet Technology · doi:10.1145/3453169 · Cited by 45 · see citing works
Duan, M., Li, K., Ouyang, A., Win, K. N., Li, K., & Tian, Q. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3379449 · Cited by 38 · see citing works
Self-citationMitigating Sybil Attacks on Differential Privacy based Federated LearningPreprint
Jiang, Y., Li, Y., Zhou, Y., & Zheng, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.10572 · Cited by 8 · see citing works
Flagged first, then by citations
1 of the 36 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Model aggregation techniques in federated learning: A comprehensive survey
Qi, P., Chiaro, D., Guzzo, A., Ianni, M., Fortino, G., & Piccialli, F. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.09.008 · Cited by 473 · see citing works
Ali, S., Li, Q., & Yousafzai, A. (2023) · Ad Hoc Networks · doi:10.1016/j.adhoc.2023.103320 · Cited by 216 · see citing works
The Impact of Adversarial Attacks on Federated Learning: A Survey
Kumar, K. N., Mohan, C. K., & Cenkeramaddi, L. R. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3322785 · Cited by 191 · see citing works
Ferrag, M. A., Friha, O., Kantarcı, B., Tihanyi, N., Cordeiro, L. C., Debbah, M. A., Hamouda, D., Al-Hawawreh, M. S., & Choo, K. R. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3317242 · Cited by 170 · see citing works
“Sybil-based collusion attack FL, DL To complete local poisoning training, the attacker employs the label flipping scheme - Image classification [166]”
BackgroundMethodWan, Y., Qu, Y., Ni, W., Xiang, Y., Gao, L., & Hossain, E. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3361451 · Cited by 152 · see citing works
“Some studies have shown that the attack success rate (ASR) of label-flipping attacks can be increased when the attacker controls more compromised clients [233], [234].”
BackgroundSurvey: federated learning data security and privacy-preserving in edge-Internet of Things
Li, H., Ge, L., & Tian, L. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10774-7 · Cited by 112 · see citing works
“…centralized FL systems to verify false node identities or use blockchain technology to implement decentralized and reliable FL in untrustworthy networks, and utilize the structural properties of the blockchain and cryptography to defend against Sybil attacks (Xiao et al. 2022; Fang et al. 2022).”
Blockchain-Based Personalized Federated Learning for Internet of Medical Things
Lian, Z., Wang, W., Han, Z., & Su, C. (2023) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2023.3279111 · Cited by 75 · see citing works
“The first is to apply technologies such as differential privacy to prevent the model from being collected and analyzed by honest but curious participants [9], to resist inference attacks [46], model inversion attacks [47], and so on.”
BackgroundMethodBlika, A., Palmos, S., Doukas, G. S., Lamprou, V., Pelekis, S., Kontoulis, M., Ntanos, C., & Askounis, D. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3449563 · Cited by 69 · see citing works
“A recent study by [225] introduced a novel form of label flipping attack specifically targeting IoT-FL systems.”
APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System
Javed, S. H., Ahmad, M. B., Asif, M., Akram, W., Mahmood, K., Das, A. K., & Shetty, S. S. (2023) · IEEE Access · doi:10.1109/access.2023.3291599 · Cited by 49 · see citing works
“Xiao et al. [27] suggest Sybil-based collusion attacks (SCA) in the I-IoT-FL system for the detection of malicious attacks.”
BackgroundExploring Adversarial Attacks in Federated Learning for Medical Imaging
Darzi, E., Dubost, F., Sijtsema, N. M., & van Ooijen, P. M. A. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3423457 · Cited by 45 · see citing works
“To counter backdoor and poisoning attacks, statistical tests identify anomalous client updates, and advanced optimization methods fortify models against such threats [10].”
A Verifiable Privacy-Preserving Federated Learning Framework Against Collusion Attacks
Chen, Y., He, S., Wang, B., Feng, Z., Zhu, G., & Tian, Z. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3516119 · Cited by 40 · see citing works
“Xiao et al. [34] put forword a Sybil-based collusion attacks (SCA) in the federated learning system for industrial Internet of Things.”
Fedcs: Efficient communication scheduling in decentralized federated learning
Zong, R., Qin, Y., Wu, F., Tang, Z., & Li, K. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102028 · Cited by 38 · see citing works
Self-citationBPFL: Blockchain-based privacy-preserving federated learning against poisoning attack
Ren, Y., Hu, M., Yang, Z., Feng, G., & Zhang, X. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120377 · Cited by 34 · see citing works
Defending Against Data Poisoning Attack in Federated Learning With Non-IID Data
Yin, C., & Zeng, Q. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2023.3296885 · Cited by 34 · see citing works
“1, some malicious users manipulate clients’ raw data and upload gradients of abnormal models to the server [9]; others modify model parameters during local training or upload incorrect gradient updates to the server [10].”
BackgroundEnhancing federated learning robustness through randomization and mixture
Nabavirazavi, S., Taheri, R., & Iyengar, S. S. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.04.009 · Cited by 30 · see citing works
Kapoor, A., & Kumar, D. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3434510 · Cited by 31 · see citing works
“Xiao et al. [195] launched a sybil attack in the IIoT in the FL setting.”
Prathiba, S. B., Govindarajan, Y., Ganesan, V. P. A., Ramachandran, A., Selvaraj, A. K., Bashir, A. K., & Gadekallu, T. R. (2024) · IEEE Access · doi:10.1109/access.2024.3401039 · Cited by 26 · see citing works
“In the realm of IIoT, the first-ever Sybil-based collusion attacks have been proposed, enabling malicious participants to manipulate model aggregation through local poisoning training [19].”
BackgroundZuo, S., Xie, Y., Wu, L., & Wu, J. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3376561 · Cited by 24 · see citing works
“For example, Xiao et al. [30] explained that under FL setting of the Industrial Internet of Things, multiple sybil nodes are virtualized to maximize the possibility of aggregation of the local poisoning models in the aggregation process.”
MethodXiao, X., Tang, Z., Li, C., Jiang, B., & Li, K. (2022) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2022.3224392 · Cited by 23 · see citing works
Self-citationCollusive Model Poisoning Attack in Decentralized Federated Learning
TAN, S., Hao, F., Gu, T., Li, L., & Liu, M. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3342901 · Cited by 22 · see citing works
“Xiao et al. [17] conducted research on sybil-based collusion attacks in IIoT, which can make the model trained based on poisoned data be aggregated by the server with a higher probability, and effectively cover up the attack behavior through collusion.”
BackgroundGAN-Driven Data Poisoning Attacks and Their Mitigation in Federated Learning Systems
Psychogyios, K., Velivassaki, T.-H., Bourou, S., Voulkidis, A. C., Skias, D., & Zahariadis, T. B. (2023) · Electronics · doi:10.3390/electronics12081805 · Cited by 21 · see citing works
Peng, J., Xing, H., Xu, L., Luo, S., Dai, P., Feng, L., Song, J. H., Zhao, B., & Xiao, Z. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3447087 · Cited by 20 · see citing works
“Xiao et al. [13] developed SCA, which achieved a substantial attack effect with fewer malicious participants and obscured their attack behavior.”
BackgroundBuilding Trusted Federated Learning: Key Technologies and Challenges
Chen, D., Jiang, X., Zhong, H., & Cui, J. (2023) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan12010013 · Cited by 20 · see citing works
Lu, R., Zhang, W., He, H. X., Li, Q., Zhong, X., Yang, H., Wang, D., Shi, L., Guo, Y., & Wang, Z. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3431555 · Cited by 16 · see citing works
“Thus, there are many kinds of attacks in the FL system, e.g., poisoning attacks [20], [21] and backdoor attacks [22], [23].”
BackgroundLi, T., Liu, A., Zhang, S., Wang, T., & Song, H. H. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125968 · Cited by 16 · see citing works
ElZemity, A., & Arief, B. (2024) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics62450.2024.00072 · Cited by 16 · see citing works
“[17], [18], [19], [20], [21], [22], [23], [24], [25], [26] Poisoning Attacks [27], [28], [29], [30] Eavesdropping [31], [32], [33] Sybil Attacks [34], [35], [36] Backdoor Attacks [37], [38], [39], [40] Gradient Leakage [41] Reconstruction [42], [43] 2) Poisoning Attacks: Adversaries intentionally…”
MethodParallel incremental association rule mining framework for public opinion analysis
Song, Y., Li, Y., Wang, Y., Xiao, X., You, S., & Tang, Z. (2023) · Information Sciences · doi:10.1016/j.ins.2023.02.034 · Cited by 15 · see citing works
Self-citationAdaptive federated few-shot feature learning with prototype rectification
Yang, M., Chu, X. Y., Zhu, J., Xi, Y., Niu, S., & Wang, Z. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107125 · Cited by 13 · see citing works
Xiao, X., Tang, Z., Li, Y., Song, Y., Tan, J., & Li, K. (2023) · IEEE Network · doi:10.1109/mnet.004.2200645 · Cited by 13 · see citing works
“…Attack: Attackers exploit system vulnerabilities to generate generate multiple sybils to carry out higher-impact attacks on selected source classes through targeted poisoning attacks (including backdoor poisoning attacks and label flipping attacks) [10, 11]. addition, more sybils can exert more”
BackgroundSelf-citationMatSwarm: trusted swarm transfer learning driven materials computation for secure big data sharing
Wang, R., Xu, C., Zhang, S., Ye, F., Tang, Y., Tang, S. H., Zhang, H., Du, W., & Zhang, X. (2024) · Nature Communications · doi:10.1038/s41467-024-53431-x · Cited by 12 · see citing works
“This centralization also makes the server susceptible to internal and external attacks 20,21 .”
Song, Y., & Liu, P. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01934-2 · Cited by 12 · see citing works
“FL has recently emerged as a promising approach for fault diagnosis as it addresses the increasing requirement for data privacy [16].”
Detection of Model Poisson Attack in Federated Learning System Using AAE in IIoT Systems
Natrayan, L. (2025) · International Conference on Electronic Circuits and Signaling Technologies (ICECST) · doi:10.1109/icecst66106.2025.11307370 · Cited by 11 · see citing works
“From the cloud, the application layer is updated with dashboards, alerts, alarms, or automated actions [5].”
An Optimal Two-Step Approach for Defense Against Poisoning Attacks in Federated Learning
Ali, Y., Han, K., Majeed, A., Lim, J. S., & Hwang, S. O. (2025) · IEEE Access · doi:10.1109/access.2025.3556906 · Cited by 11 · see citing works
“…are two primary categories of poisoning attacks: data poisoning (DP), where the attacker manipulates the client’s data labels or introduces noise into the data [6], [7], and model poisoning (MP), where the attacker manipulates the training process or directly crafts random LM parameters [8], [9].”
The Convergence of AI/ML and Cybersecurity: Advancing Digital Forensic Techniques
Iyengar, S. S., Nabavirazavi, S., Hariprasad, Y., Prasad, H. B., & Mohan, C. K. (2025) · Signals and communication technology · doi:10.1007/978-3-031-89327-8_4 · Cited by 12 · see citing works
Collusion-Based Poisoning Attacks Against Blockchained Federated Learning
Zhang, X., Shen, T., Bai, F., & Zhang, C. (2023) · IEEE Network · doi:10.1109/mnet.2023.3318179 · Cited by 10 · see citing works
“A rt In this part, our CPA is contrasted with the state-of-the-art attack method-SCA [8].”
MethodAhmad, K. M., Liu, Q., Khan, A. A., Gan, Y., & Lin, R. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124828 · Cited by 10 · see citing works
FedG2L: a privacy-preserving federated learning scheme base on “G2L” against poisoning attack
Xu, M., & Li, X. (2023) · Connection Science · doi:10.1080/09540091.2023.2197173 · Cited by 9 · see citing works
“But there are still some challenges of benchmark gradient dependence (Li et al., 2023; Xiao et al., 2023).”
BackgroundTEG-DI: Dynamic incentive model for Federated Learning based on Tripartite Evolutionary Game
Xu, J., Zhao, Y., Li, X., Zhou, L., Zhu, K., Xu, X., Duan, Q., & Zhang, R. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.129259 · Cited by 9 · see citing works
VerifBFL: Leveraging zk-SNARKs for a Verifiable Blockchained Federated Learning
Bellachia, A. A., Bouchiha, M. A., Ghamri-Doudane, Y. M., & Rabah, M. (2025) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms57970.2025.11073628 · Cited by 10 · see citing works
“In BFL systems, where participants are supposed to act independently and without prior knowledge of each other’s data or intentions [27], this type of attack can enable adversaries to bypass some verification strategies or manipulate the behavior of the resulting global model.”
Zhao, H., Sui, M., Liu, M., Zhu, C., Xun, W., Xu, B., & Zhu, H. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3367875 · Cited by 10 · see citing works
“Additionally, due to FL’s emphasis on preserving client data privacy, the central server cannot verify the local data of all clients, making it challenging to detect malicious clients [14].”
BackgroundData Splitting Based Double Layer Encryption for Secure Ciphertext Deduplication in Cloud Storage
Tang, X., & Jin, L. (2024) · IEEE ... International Conference on Cloud Computing · doi:10.1109/cloud62652.2024.00027 · Cited by 8 · see citing works
“Furthermore, the schemes introduced above suffer from the collusion attack [30], where a malicious CSP may collaborate with one or more user to violate the privacy of other ones.”
BackgroundMali, B., Singh, P. K., & Mazumdar, N. (2024) · Security and Privacy · doi:10.1002/spy2.403 · Cited by 7 · see citing works
“In parallel, Xiao et al. 32 conducted a simulation-based analysis, employing the label flipping method to poison substantial data generated by an Industrial Internet of Things (IIoT) device.”
Kaushal, V., & Sharma, S. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02339-z · Cited by 7 · see citing works
Ariffin, A., Afifi, F., Zaki, F., Hanif, H., & Anuar, N. B. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111471 · Cited by 7 · see citing works
A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly Detection
Nguyen, V.-D., Diro, A. A., Chilamkurti, N., Heyne, W., & Phan, K. T. (2025) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2025.3585842 · Cited by 7 · see citing works
“An intrinsic limitation of our proposed blockchain-enabled Federated Learning (FL) system is its potential vulnerability to Sybil attacks, as identified in recent research [39].”
Ensuring trustworthy and secure IoT: Fundamentals, threats, solutions, and future hotspots
Huang, M., Peng, Q., Zhu, X., Deng, T., Cao, R., & Liu, W. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111218 · Cited by 7 · see citing works
Ashwini, P., & Rout, R. R. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111656 · Cited by 6 · see citing works
A Manifold Consistency Interpolation Method of Poisoning Attacks Against Semi-Supervised Model
Wang, X., Wang, X., He, M., Zhang, M., & Zhang, Z. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3268882 · Cited by 6 · see citing works
Song, Y., Ai, Y., Xiao, X., Liu, Z., Tang, Z., & Li, K. (2024) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2024.103070 · Cited by 6 · see citing works
Self-citationKazemi, K., Badiei, M. H., & Kebriaei, H. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3571872 · Cited by 5 · see citing works
“These attacks disrupt the learning process through techniques such as model corruption, which degrades learning performance or embeds hidden triggers, and data poisoning, which biases training data [11].”
Efficient Sharing of Energy Consumption Data: A Privacy-Preserving Threshold Aggregation Approach
Li, G., Zhou, L., Lian, J., Liu, S., Yang, L., Zhong, Y., & Li, Q. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3554576 · Cited by 5 · see citing works
“Nongoal : Sybil attacks [35] are not within our scope.”
Investigated Insider and Outsider Attacks on the Federated Learning Systems
Ahmed, I. M., & Kashmoola, M. Y. (2022) · IEEE International Conference on Communication, Networks and Satellite (COMNETSAT) · doi:10.1109/comnetsat56033.2022.9994330 · Cited by 6 · see citing works
“[11], Sybil-based Collusion Attacks (SCA) for the IIoT-FL system have been proposed to fix the flaws bad guys make in label-flipping attacks to identify poisonings in their area and simulate multiple Sybil nodes by default to make local Sybil models aggregate as likely as possible during compilation.”
MethodTrust Online Over-the-Air Computation for Wireless Federated Learning
Sun, M., Zheng, J., Du, H., Zhang, H., Niyato, D. T., Kang, J., Wang, J., Ren, J., Gao, L. C., & Wang, Z. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3547148 · Cited by 4 · see citing works
B2DFL: Bringing butterfly to decentralized federated learning assisted with blockchain
Wang, H. H., Cai, Y., Tao, Y., Wang, L., Li, Y., & Zhou, L. (2024) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2024.104978 · Cited by 4 · see citing works
Xue, M., Zhong, H., Shi, Y., Zeng, Y., Zhang, J., & Zhao, N. (2025) · Cybersecurity · doi:10.1186/s42400-025-00366-5 · Cited by 3 · see citing works
“Addiltionaly, when each malicious participant employs a collusive approach to deceive the auditing process (such as Sybil attacks Xiao et al. 2022), the audit-based methods become directly ineffective.”
Ariffin, A., Zaki, F., Hanif, H., & Anuar, N. B. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111739 · Cited by 3 · see citing works
Ariffin, A., Zaki, F., Hanif, H., & Anuar, N. B. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3215 · Cited by 3 · see citing works
TDC-Cache: A Trustworthy Decentralized Cooperative Caching Framework for Web3.0
Chen, J., Shi, L. X., Wang, T., Wang, J., & Zhang, W. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3643947 · Cited by 3 · see citing works
“Even if colluders succeed in electing a malicious training oracle by submitting falsified cooperative proofs [41], the elected oracle is required to complete the training task; otherwise, its model update would fail to obtain sufficient votes during the Commit phase.”
Xiao, X., Duan, M., Song, Y., Tang, Z., & Yang, W. (2024) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3649329.3655934 · Cited by 3 · see citing works
“They can leverage dirty labels for poisoning [15] [19], or inject trojans into training samples and activate backdoors [6] [17].”
Self-citationBSFL: A blockchain-oriented secure federated learning scheme for 5G
Han, G., Ma, W., Zhang, Y., Liu, Y., & Liu, S. (2025) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2025.103983 · Cited by 3 · see citing works
GCPA: GAN-Based Collusive Poisoning Attack in Federated Recommender Systems
Gu, T., TAN, S., Hao, F., Liu, X., Chang, L., & Liu, Y. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3579807 · Cited by 2 · see citing works
“…poisoning attacks and collusive poisoning attacks have focused on altering the exposure of specific items with poisoned updates (i.e., local model updates from malicious users) [12], [13], [14], [15], [16], [17], and the targeted collusive poisoning attacks have only focused on FL [28], [29].”
Tang, Y., Ni, L., Zhang, J., & Liang, Y. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112209 · Cited by 2 · see citing works
MPHM: Model poisoning attacks on federal learning using historical information momentum
Shi, L., Chen, Z., Shi, Y., Lin, W., Tao, Y., He, M., Wang, Q., Zhou, Y. H., & Gao, Y. (2023) · Security and Safety · doi:10.1051/sands/2023006 · Cited by 2 · see citing works
AF-MCDC: Active Feedback-Based Malicious Client Dynamic Detection
Du, H., Zhang, S., Xv, X., Ji, Y. Y., Shao, S., Wu, F., & Liu, S. (2025) · Computer Networks · doi:10.1016/j.comnet.2025.111234 · Cited by 2 · see citing works
Defending Against Poisoning Attacks in Federated Prototype Learning on Non-IID Data
Zhang, J., Zhang, H., Wang, G., & Dong, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71467-2_6 · Cited by 1 · see citing works
Federated Learning Poison Attack Detection Scheme Based on Gradient Similarity
Zhao, Q., Zhang, Y., Jing, Z., Zhou, Y., & Xin, Z. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-80419-9_2 · Cited by 1 · see citing works
Bitcoin attacks: A comprehensive study
Sofi, A. A., Mir, A. H., & Jabeen, Z. (2025) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2025.104297 · Cited by 2 · see citing works
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 · see citing works
“The attacker controls a clients, similar to Sybil attacks [22], either by injecting fake clients or compromising real ones.”
Tan, J., Zhang, J., Tang, Z., Xiao, X., Jiang, B., Zhao, J., & Li, K. (2025) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/3776583 · Cited by 1 · see citing works
Self-citationFedMSD: Multi-Stage Defense Against Poisoning Attacks in Data Heterogeneous Federated Learning
Zhang, X., Tong, F., & Xing, F. (2024) · International Conference on Artificial Intelligence of Things and Systems (AIoTSys) · doi:10.1109/aiotsys63104.2024.10780671 · Cited by 1 · see citing works
“The second issue is the lack of schemes capable of de-fending against both non-collusion and collusion attacks [7].”
MCA: Model Compromise Attacks against Federated Computing Power Networks
Zhang, K., Xiao, X., Peng, Z., & Cai, M. (2023) · International Conference on Electronics, Computers and Communication Technology (CECCT) · doi:10.1145/3637494.3638734
“Unfortunately, many recent studies [13] [11] have shown that although the FL system keeps the data locally, there are still substantial security risks.”
BackgroundSelf-citationUnveiling Threats to Bitcoin: Exploring Attacks, Vulnerabilities, and Network IntegrityPreprint
Sofi, A. A., Mir, A. H., & Jabeen, Z. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4817068
Communication Optimization in Blockchain Peer-to-Peer Networks
Zhang, K., Peng, Z., Zong, R., Wang, Q., Xiao, X., & Tang, Z. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580841
“Various blockchain-based frameworks have been seamlessly integrated into diverse domains[4], [5], [6], including health-care, finance, federated learning, and more.”
BackgroundSelf-citationFedSV: A Privacy-Preserving Byzantine-Robust Federated Learning Scheme with Self-validation
Jiang, W., Fu, S., Luo, Y., Liu, L., & Wang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-1525-4_13
PSO-Meme: An Efficient and Secure RSU Deployment Scheme for IoV
Wu, X., Guo, H., Zhou, X., Mao, B., Liu, J., & Xun, Y. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901630
“Among many current defense solutions, the most common one is multi-intelligence joint identification [11], which is also closely related to the location deployment of RSUs.”
KAFQN: Kolmogorov-Arnold Fuzzy-guided Q-Network in Reinforcement Learning
Zhao, B., Liu, Z., & Tang, Z. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890744
Self-citationRanjan, R., Saini, M., & Bhushan, B. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-3728-7_32
FRFL: Fair and Robust Federated Learning Incentive Model Based on Game Theory
Ye, H., Zhou, L., Wang, H. H., & Ge, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9101-2_10
A distributed bijection-backdoor-based adversarial examples defense method in federated learning
Li, Y., Guo, Y., Chen, F., Wang, Y., Chen, Q., & Hu, Y. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02750-6
“…in [19], and model replacement as detailed in [20]; (2) Privacy inference attacks, such as membership inference as per [21] and model inversion as reported in [22]; (3) Free-riding attacks, as explored in [23]; (4) Sybil attacks, which are discussed in [24, 25]; (5) Adversarial example attacks.”
Zhukabayeva, T. K., Adamova, A., Abdildayeva, A. A., & Karabayev, N. (2025) · Scientific Journal of Astana IT University · doi:10.37943/22doku3034
Privacy-Preserving Threshold Enforcement Aggregation with Fault TolerancePreprint
Li, G., Jiang, Q. G., Zhou, L., Yang, L., Liu, L., & Ma, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5450718
su, Q., Zhang, G., li, H., & Ge, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5506730
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
FedMPQ: Secure and Efficient Federated Learning with Multi-codebook Product Quantization
Xu, Y., Tang, Z., Hao, B., Xiao, X., & Zhang, J. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209457
Self-citationRDCBA-FEL: Robust Defense Against Colluded Backdoor Attacks in Federated Edge Learning
Zhang, P., Xu, L., Xu, C., Mei, L., & Liu, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3629550
“The above studies work well against traditional BAs, but their e ff ectiveness diminishes with the emergence of colluded backdoor attacks (CBAs) [13].”
Power to the Clients: Federated Learning in a Dictatorship Setting
Alipour, M., & Amiri, M. M. (2026) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit62367.2026.11654134
“These clients may exchange information and strategically craft updates that steer the aggregated model toward a compromised state.”
Sybil-based Virtual Data Poisoning Attacks in Federated Learning
朱昌勳, Wu, Q., Lyu, L., & Xue, S. (2025) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit66093.2025.11321374
“Inspired by this work, Refs.”
LiFeChain: Lightweight Blockchain for Secure and Efficient Federated Lifelong Learning in IoT
Chen, H., Deng, J., Wu, X., Jiang, Z., Zhang, X., Chen, X. Y., Ngai, E. C. ‐., & Liu, J. (2026) · IEEE Transactions on Networking · doi:10.1109/ton.2026.3685160
“Furthermore, collusive attacks by multiple servers can disrupt the learning process [17].”
Xiao, X., Tang, Z., Song, Y., Tan, J., Wang, X., Chen, L. N., Liang, Z., & Li, K. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3686756
“…adversaries can also execute data poisoning attacks during the local training phase, and attackers can employ label flipping attacks [23], [24], [25] or embed backdoor triggers [26], [27], [28] into local training samples to misclassify targeted samples during the testing phase of the…”
Self-citationAli, W., Altulyan, M. S., Ihnaini, B., Zhou, X., & Shao, J. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11579-6
Zhang, Z., Zhang, C., Chen, G., Xiao, S., & Huang, L. (2026) · Decision Support Systems · doi:10.1016/j.dss.2026.114703
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
A Robust Aggregation for Federated Learning Using Shapley Value and Fisher Information
Zhong, Y., Wang, Z. P., & Wang, X. (2026) · International Conference on Sensor-Cloud and Edge Computing System (SCECS) · doi:10.1109/scecs69812.2026.11565903
“In data poisoning attacks, adversaries primarily aim to corrupt the local training data of clients, thereby indirectly inducing compromised clients to generate model updates that deviate from the expected distribution [6].”
He, Y., Ye, R., & Zhang, Z. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3708675
“The adversary can launch adversarial attacks such as model evasion and poisoning attacks [8], [9].”
Chen, D., Chen, X., Wang, Z., Wang, J., Shi, L., & Zhou, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-9284-5_3
Poisoning resilient federated learning for secure internet of medical things a systematic review
Unbreen, A., Naeem, H., Hassan, S. R., & Hassan, A. S. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02344-3
“Adversaries can capture or delay, which causes erroneous aggregation and eventual deterioration of model behavior [74, 76].”
InfluentialMohcine, B., & Bouzidi, D. (2026) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp6050168
“Advanced Sybil mechanisms deploy behavioral switching to dynamically adjust fake identities under detection pressure, subverting static heuristic thresholds [11].”
Cross-Modal Data Integrity Verification in Distributed Transit Networks
Rakhimzhanov, D., Adamova, A., Mansurova, A., & Yedilkhan, D. (2026) · International Conference on Advanced Machine Learning and Data Science (AMLDS) · doi:10.1109/amlds69611.2026.11723686
“…Sybil-based collusion attacks, where malicious entities use multiple fake identities to amplify the effect of label flipping attacks, specifically targeting critical classes that could disrupt transit predictions or traffic flow management, while preserving overall accuracy to evade detection [14].”
FedSPA: an attack-tolerant robust federated aggregation via shapley value and parameter analysis
Zhong, Y., Xue, G., Wang, Z., & Liu, J. (2026) · Cluster Computing · doi:10.1007/s10586-026-06703-8
- Authors
- Xiao, X., Tang, Z., Li, C., Xiao, B., & Li, K.
- Affiliations
- Hong Kong Polytechnic University (HK)
- Hunan University (CN)
- Venue
- IEEE Transactions on Industrial Informatics
- Published
- 2023-03
- Volume
- 19
- Issue
- 3
- Pages
- 2608-2618
- ISSN
- 1551-3203 (ISSN-L)
- 1941-0050
- OpenAlex
- W4285205197
- Cited by
- 99
- References
- 36
- Citations by year
- 2026: 14 · 2025: 35 · 2024: 28 · 2023: 20 · 2022: 2
- FWCI
- 6.99
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Industrial Informatics (publishedVersion)
- Funders
- National Key Research and Development Program of China (2018YFB1701400)
- National Natural Science Foundation of China (92055213, 61873090, L1924056)
- Guangdong Province Research and Development Plan Project in Key Area (2020B0101100001)
- China Knowledge Centre for Engineering Sciences and Technology Project (CKCEST-2021-2-7)
- Shenzhen Development and Reform Commission Strategic Emerging Industry Development Project (XMHT20190205007)
- 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 › Network Security and Intrusion Detection
- Keywords
- data poisoning, federated learning, Industrial Internet of Things, label-flipping attacks, model aggregation, malicious participants, data privacy
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
