Exploring Adversarial Graph Autoencoders to Manipulate Federated Learning in The Internet of Things
Abstract
Mobile edge computing (MEC) enables the Internet of Things (IoT) with seamless integration of multiple application services. Federated learning is increasingly considered to improve training accuracy in MEC-IoT while circumventing the disclosure of private data, where the IoT nodes collaboratively train a machine learning model without disclosing their private data. In this paper, we propose a new cyber-epidemic attack that progressively manipulates federated learning and reduces the training accuracy of the benign MEC-IoT. The proposed cyber-epidemic attack explores adversarial graph autoencoders (GACE) to generate malicious local model updates that extract correlated features with the benign local and global models. The proposed GACE attack epidemically infects all the benign IoT nodes along with the training iterations in federated learning, while highly enhancing concealment of the attack.
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?
With the broadcast nature of wireless interfaces, adversaries can potentially overhear local model updates from multiple or even all clients and create malicious local models to compromise WFL.
“Moreover, with the broadcast nature of wireless interfaces, adversaries can potentially overhear local model updates from multiple or even all clients and accordingly create malicious local models to compromise WFL, e.g., using generative neural networks and machine learning technologies.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [114]
A rogue client can collect local model updates that benign clients upload, take them as input to a graph adversarial encoder (GAE) to produce a malicious local model update, which can poison WFL and stop or slow down its convergence.
“For example, in [35], [114], a new adversarial attack on WFL is studied by exploiting the broadcast nature of wireless channels, where a rogue client collects the local model updates that benign clients upload. The rogue client can take these overheard local model updates as input to a graph adversarial encoder (GAE) to produce a malicious local model update. The malicious local model update can”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [114]
Cites
1 retracted
Poongodi, M., Walia, R., Iwendi, C., Ahanger, T. A., Suganthi, S. T., Kamruzzaman, M. M., Bourouis, S., Alhakami, W., & Hamdi, M. (2022) · Expert Systems · doi:10.1111/exsy.13072 · Cited by 62 · see citing works
RetractedData 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
Ghimire, B., & Rawat, D. B. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3150363 · Cited by 497 · see citing works
A Survey on Security and Privacy Issues in Edge-Computing-Assisted Internet of Things
Alwarafy, A., Al-Thelaya, K., Abdallah, M. M., Schneider, J., & Hamdi, M. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3015432 · Cited by 436 · see citing works
Zhang, Z., Cao, X., Jia, J., & Gong, N. Z. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539231 · Cited by 359 · see citing works
Shejwalkar, V., Houmansadr, A., Kairouz, P., & Ramage, D. (2022) · 2022 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp46214.2022.9833647 · Cited by 292 · see citing works
Edge and fog computing for IoT: A survey on current research activities & future directions
Laroui, M., Nour, B., Moungla, H., Cherif, M. A., Afifi, H., & Guizani, M. (2021) · Computer Communications · doi:10.1016/j.comcom.2021.09.003 · Cited by 290 · see citing works
Self-citationWhen Internet of Things Meets Metaverse: Convergence of Physical and Cyber Worlds
Li, K., Cui, Y., Li, W., Lv, T., Yuan, X., Li, S., Ni, W., Simsek, M., & Dressler, F. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3232845 · Cited by 289 · see citing works
Self-citationPoisoning Attack in Federated Learning using Generative Adversarial Nets
Zhang, J., Chen, J., Wu, D., Chen, B., & Yu, S. (2019) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom/bigdatase.2019.00057 · Cited by 216 · see citing works
Energy-Efficient Cooperative Relaying for Unmanned Aerial Vehicles
Li, K., Ni, W., Wang, X., Liu, R. P., Kanhere, S. S., & Jha, S. K. (2015) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2015.2467381 · Cited by 202 · see citing works
Self-citationPoisoning Attacks on Federated Learning-based IoT Intrusion Detection System
Nguyen, T. D., Rieger, P., Miettinen, M., & Sadeghi, A.-R. (2020) · Proceedings 2020 Workshop on Decentralized IoT Systems and Security · doi:10.14722/diss.2020.23003 · Cited by 200 · see citing works
Deep Model Poisoning Attack on Federated Learning
Zhou, X., Xu, M., Wu, Y., & Zheng, N. (2021) · Future Internet · doi:10.3390/fi13030073 · Cited by 170 · see citing works
LoMar: A Local Defense Against Poisoning Attack on Federated Learning
Li, X., Qu, Z., Zhao, S., Tang, B., Lu, Z., & Liu, Y. (2021) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3135422 · Cited by 152 · see citing works
Intelligent Task Offloading for Heterogeneous V2X Communications
Xiong, K., Leng, S., Huang, C., Yuen, C., & Guan, Y. L. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3015210 · Cited by 142 · see citing works
Energy Efficient Legitimate Wireless Surveillance of UAV Communications
Li, K., Voicu, R. C., Kanhere, S. S., Ni, W., & Tovar, E. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2890999 · Cited by 107 · see citing works
Self-citationZheng, J., Li, K., Mhaisen, N., Ni, W., Tovar, E., & Guizani, M. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3176739 · Cited by 87 · see citing works
Self-citationLi, K., Ni, W., & Dressler, F. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3102831 · Cited by 58 · see citing works
Self-citationBorgiani, V., Moratori, P., Kazienko, J. F., Tubino, E. R. R., & Quincozes, S. E. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3028652 · Cited by 56 · see citing works
A Critical Evaluation of Privacy and Security Threats in Federated Learning
Asad, M., Moustafa, A., & Yu, C. (2020) · Sensors · doi:10.3390/s20247182 · Cited by 51 · see citing works
Federated Learning for Energy-balanced Client Selection in Mobile Edge Computing
Zheng, J., Li, K., Tovar, E., & Guizani, M. (2021) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc51323.2021.9498853 · Cited by 48 · see citing works
Self-citationMoat: Model Agnostic Defense against Targeted Poisoning Attacks in Federated Learning
Manna, A., Kasyap, H., & Tripathy, S. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-86890-1_3 · Cited by 22 · see citing works
Information Stealing in Federated Learning Systems Based on Generative Adversarial Networks
Sun, Y., Chong, N. S. T., & Ochiai, H. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9658652 · Cited by 13 · see citing works
A Hybrid Deep Learning Model for UAVs Detection in Day and Night Dual Visions
Noor, A., Li, K., Ammar, A., Koubâa, A., Benjdira, B., & Tovar, E. (2021) · IEEE International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi52975.2021.00037 · Cited by 11 · see citing works
Self-citationLi, K., Ni, W., Zheng, J., Tovar, E., & Guizani, M. (2021) · IEEE Network · doi:10.1109/mnet.011.2000538 · Cited by 9 · see citing works
Self-citationMakkar, S., & Sharma, L. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9942-8_1 · Cited by 5 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Wan, 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
“For example, in [35], [114], a new adversarial attack on WFL is studied by exploiting the broadcast nature of wireless channels, where a rogue client collects the local model updates that benign clients upload.”
BackgroundSelf-citationData-Agnostic Model Poisoning Against Federated Learning: A Graph Autoencoder Approach
Li, K., Zheng, J., Yuan, X., Ni, W., Akan, O. B., & Poor, H. V. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3362147 · Cited by 41 · see citing works
Self-citationLeverage Variational Graph Representation for Model Poisoning on Federated Learning
Li, K., Yuan, X., Zheng, J., Ni, W., Dressler, F., & Jamalipour, A. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3394252 · Cited by 20 · see citing works
Self-citationExploring Representational Similarity Analysis to Protect Federated Learning from Data Poisoning
Chen, G., Li, K., Abdelmoniem, A. M., & You, L. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589335.3651503 · Cited by 13 · see citing works
Self-citationBiasing Federated Learning With a New Adversarial Graph Attention Network
Li, K., Zheng, J., Ni, W., Huang, H., Lió, P., Dressler, F., & Akan, Ö. B. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3499371 · Cited by 9 · see citing works
Self-citationLi, K., Liang, Y., Lió, P., Ni, W., Dressler, F., Crowcroft, J., & Akan, Ö. B. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3636440 · Cited by 3 · see citing works
Self-citationBiasing Federated Learning Based on Adversarial Graph Attention Networks
Li, K., Yuan, X., & Ni, W. (2026) · Springer series in reliability engineering · doi:10.1007/978-3-032-23959-4_5
Self-citationLi, K., Yuan, X., & Ni, W. (2026) · Springer series in reliability engineering · doi:10.1007/978-3-032-23959-4_6
Self-citation
- Authors
- Li, K., Yuan, X., Zheng, J., Ni, W., & Guizani, M.
- Affiliations
- Centro de Investigação em Sistemas Computacionais Embebidos e de Tempo-Real (PT)
- Commonwealth Scientific and Industrial Research Organisation (AU)
- Mohamed bin Zayed University of Artificial Intelligence (AE)
- Venue
- 2023 International Wireless Communications and Mobile Computing (IWCMC)
- Publisher
- IEEE
- Published
- 2023-06-19
- Pages
- 898-903
- OpenAlex
- W4385079041
- Cited by
- 8
- References
- 25
- Citations by year
- 2026: 2 · 2025: 1 · 2024: 5
- FWCI
- 1.42
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Wireless Communications and Mobile Computing Conference (IWCMC) (publishedVersion)
- OPUS - Open Publications of UTS Scholars (University of Technology Sydney) (submittedVersion)
- 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 › IoT and Edge/Fog Computing
- Keywords
- federated learning, Internet of Things, mobile edge computing, attack concealment, privacy-preserving machine learning
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
