Uncovering Malicious Accounts in Online Social Networks Using XGBoost and Graph Convolution Networks
Abstract
In this work, we introduce a Machine-Learning (ML) approach based on XGBoost and Graph Convolutional Networks (GCNs) for the detection of active malicious accounts in Online Social Networks (OSN). Distinguishing itself from previous detection algorithms by relying on user relationships, our approach combines heterogeneous information, including descriptive user features and inter-user relationship data, to obtain advanced user representations for determining their legitimacy. Specifically, we employ the XGBoost algorithm to extract crucial features, mitigating the impact of redundant ones. Next, we utilize the Graph Convolutional Networks approach to derive advanced user representations based on the actual relationships between malicious accounts and the descriptive features of users, and lastly, we employ the sigmoid function to assess user legitimacy based on their high-level feature matrices. Experimental results depict that the proposed XGBoost-based approach outperforms other feature selection methods, and comparison with other account detection algorithms shows superior efficiency, accuracy, and flexibility.
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?
Experiments based on Random Forest and XGBoost classifiers have proven to perform well in dealing with structured data.
“Experiments based on RF and XGBoost (XGB)55 classifiers have proven to perform well in dealing with structured data.”
From Instagram fake profile detection using an ensemble learning method (2025) · cites this paper as [55]
Cites
Feature Selection: A Data Perspective
Li, J., Cheng, K., Wang, S., Morstatter, F., Trevino, R. P., Tang, J., & Liu, H. (2018) · ACM Computing Surveys · doi:10.1145/3136625 · Cited by 2,442 · see citing works
Detecting spammers on social networks
Stringhini, G., Kruegel, C., & Vigna, G. (2010) · Proceedings of the 26th Annual Computer Security Applications Conference · doi:10.1145/1920261.1920263 · Cited by 791 · see citing works
Zhou, X., Liang, W., Wang, K. I., et al. (2020) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2020.2987846 · Cited by 286 · see citing works
Uncovering Large Groups of Active Malicious Accounts in Online Social Networks
Cao, Q., Yang, X., Yu, J., & Palow, C. (2014) · Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2660267.2660269 · Cited by 274 · see citing works
PDPChain: A Consortium Blockchain-Based Privacy Protection Scheme for Personal Data
Liang, W., Yang, Y., Yang, C., Hu, Y., Xie, S., Li, K., & Cao, J. (2022) · IEEE Transactions on Reliability · doi:10.1109/tr.2022.3190932 · Cited by 234 · see citing works
Self-citationZhou, X., Ye, X., Wang, K. I., Liang, W., Nair, N. C., Shimizu, S., Yan, Z., & Jin, Q. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2023.3259431 · Cited by 232 · see citing works
Zhou, X., Zheng, X., Cui, X., Shi, J., Liang, W., Yan, Z., Yang, L. T., Shimizu, S., & Wang, K. I. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3310046 · Cited by 192 · see citing works
An Intelligent Intrusion Detection System for Smart Consumer Electronics Network
Javeed, D., Saeed, M. S., Ahmad, I., Kumar, P., Jolfaei, A., & Tahir, M. A. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3277856 · Cited by 177 · see citing works
Zhou, X., Liang, W., Wang, K. I., & Shimizu, S. (2019) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2019.2918285 · Cited by 168 · see citing works
Zhou, X., Yang, Q., Zheng, X., Liang, W., Wang, K. I., Ma, J., Pan, Y. F., & Jin, Q. (2024) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2023.3345431 · Cited by 152 · see citing works
Rough set based semi-supervised feature selection via ensemble selector
Liu, K., Yang, X., Yu, H., et al. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.11.034 · Cited by 135 · see citing works
GTxChain: A Secure IoT Smart Blockchain Architecture Based on Graph Neural Network
Cai, J., Liang, W., Li, X., et al. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3296469 · Cited by 130 · see citing works
Zhou, X., Yang, Q., Liu, Q., et al. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102182 · Cited by 130 · see citing works
Zhou, X., Zheng, X., Shu, T., et al. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3330864 · Cited by 122 · see citing works
Sybil Attack in RPL-Based Internet of Things: Analysis and Defenses
Pu, C. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2971463 · Cited by 119 · see citing works
Zhou, X., Huang, W., Liang, W. Y., Yan, Z., Ma, J., Pan, Y., & Wang, K. I. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120217 · Cited by 104 · see citing works
Zheng, J., Pan, H., Tong, J., et al. (2021) · ISA Transactions · doi:10.1016/j.isatra.2021.05.042 · Cited by 97 · see citing works
A Regularized Cross-Layer Ladder Network for Intrusion Detection in Industrial Internet of Things
Long, J., Liang, W., Li, K., Wei, Y., & Marino, M. D. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3204034 · Cited by 86 · see citing works
Self-citationEfficient Semi-Supervised Feature Selection: Constraint, Relevance, and Redundancy
Benabdeslem, K., & Hindawi, M. (2013) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.86 · Cited by 85 · see citing works
Sybil defenses via social networks
Yu, H. (2011) · ACM SIGACT News · doi:10.1145/2034575.2034593 · Cited by 84 · see citing works
Leveraging Analysis of User Behavior to Identify Malicious Activities in Large-Scale Social Networks
Al‐Qurishi, M., Hossain, M. S., Alrubaian, M., Rahman, S. M. M., & Alamri, A. M. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2753202 · Cited by 83 · see citing works
A Mutual Security Authentication Method for RFID-PUF Circuit Based on Deep Learning
Liang, W., Xie, S., Zhang, D., Li, X., & Li, K. (2021) · ACM Transactions on Internet Technology · doi:10.1145/3426968 · Cited by 78 · see citing works
Self-citationHaghighi, M. S., Farivar, F., Jolfaei, A., Asl, A. B., & Zhou, W. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3297965 · Cited by 70 · see citing works
Shin, K., Hooi, B., Kim, J., & Faloutsos, C. (2017) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3018661.3018676 · Cited by 57 · see citing works
Blockchain Assisted Hybrid Intrusion Detection System in Autonomous Vehicles for Industry 5.0
Anbalagan, S., Raja, G., Gurumoorthy, S., et al. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3320282 · Cited by 57 · see citing works
TrustBCFL: Mitigating Data Bias in IoT Through Blockchain-Enabled Federated Learning
Zhou, S., Li, K. C., Chen, Y.-X., Yang, C., Liang, W., & Zomaya, A. Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3379363 · Cited by 47 · see citing works
Self-citationIntelligent ontology based semantic information retrieval using feature selection and classification
Selvalakshmi, B., & Subramaniam, M. (2018) · Cluster Computing · doi:10.1007/s10586-018-1789-8 · Cited by 44 · see citing works
MC-DSC: A Dynamic Secure Resource Configuration Scheme Based on Medical Consortium Blockchain
Liang, W., Xie, S., Li, K., et al. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3364370 · Cited by 44 · see citing works
Self-citationValidating the integrity of Convolutional Neural Network predictions based on zero-knowledge proof
Fan, Y., Xu, B., Zhang, L., Song, J., Zomaya, A. Y., & Li, K. (2023) · Information Sciences · doi:10.1016/j.ins.2023.01.036 · Cited by 33 · see citing works
Self-citationA Trajectory Privacy-Preserving Scheme Based on Transition Matrix and Caching for IIoT
Zhang, S., Hu, B., Liang, W., Li, K., & Pathan, A. K. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3308073 · Cited by 33 · see citing works
Self-citationAmrit, P., Singh, A. K., Singh, M. P., et al. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3283284 · Cited by 30 · see citing works
LightNestle: Quick and Accurate Neural Sequential Tensor Completion via Meta Learning
Li, Y., Liang, W., Xie, K., et al. (2023) · doi:10.1109/infocom53939.2023.10228967 · Cited by 29 · see citing works
Wang, X., Wang, Z., Zhang, Y., et al. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10474-8 · Cited by 27 · see citing works
DeepOSN: Bringing deep learning as malicious detection scheme in online social network
Wanda, P., Hiswati, M. E., & Jie, H. J. (2020) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v9.i1.pp146-154 · Cited by 23 · see citing works
Logistic local hyperplane-Relief: A feature weighting method for classification
Zhang, L., Huang, X., & Zhou, W. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.04.011 · Cited by 14 · see citing works
Predictable Model for Detecting Sybil Attacks in Mobile Social Networks
Lyu, C., Huang, D., Jia, Q., Xiao, H., Zhang, X., Chi, C., & Xu, Y. (2021) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc49053.2021.9417254 · Cited by 7 · see citing works
Credit decision system based on combination weight and eXtreme Gradient Boosting algorithm
Chen, Y., Kaiyun, B., & Jiangtian, C. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1955/1/012081 · Cited by 6 · see citing works
Between Overload and Indifference: Detection of Fake Accounts and Social Bots by Community Managers
Boberg, S., Frischlich, L., Schatto‐Eckrodt, T., Wintterlin, F., & Quandt, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-39627-5_2 · Cited by 4 · see citing works
Chen, J., & Tang, G. (2021) · Journal of Signal Processing Systems · doi:10.1007/s11265-021-01637-3 · Cited by 3 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Instagram fake profile detection using an ensemble learning method
Goyal, B., Gill, N. S., Gulia, P., Alduaiji, N., Shukla, P. K., & J, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-03973-x · Cited by 10 · see citing works
- Authors
- Tang, Y., Zhang, D., Li, K.-C., & Yuan, J.
- Affiliations
- Hunan University (CN)
- Providence University (TW)
- University at Buffalo, State University of New York (US)
- Venue
- IEEE Transactions on Consumer Electronics
- Published
- 2025-05
- Volume
- 71
- Issue
- 2
- Pages
- 6489-6498
- ISSN
- 0098-3063 (ISSN-L)
- 1558-4127
- OpenAlex
- W4399039675
- Cited by
- 6
- References
- 39
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 1
- FWCI
- 2.26
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Consumer Electronics (publishedVersion)
- Funders
- National Natural Science Foundation of China (62072170, 61872138)
- Topics
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Keywords
- malicious account detection, social networking sites, XGBoost, graph convolutional networks, feature selection, user representation 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
