The week's pick
Random Articles
Reseach Article
Graph Convolutional Representation Learning for Sybil Detection in Online Social Networks
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 89 |
| Year of Publication: 2026 |
| Authors: Heta Dasondi, Meghna B. Patel, Satyen M. Parikh |
10.5120/ijca2026926566
|
Heta Dasondi, Meghna B. Patel, Satyen M. Parikh . Graph Convolutional Representation Learning for Sybil Detection in Online Social Networks. International Journal of Computer Applications. 187, 89 ( Mar 2026), 53-58. DOI=10.5120/ijca2026926566
Abstract
Online Social Networks (OSNs) are increasingly vulnerable to Sybil attacks, wherein adversaries create numerous fake identities to distort information, manipulate influence, and compromise user trust. Existing detection methods, while effective in constrained settings, often struggle to scale and generalize across the complex and dynamic topologies of modern social graphs. In this paper, it propose SD-GCN, a scalable Sybil detection framework based on Graph Convolutional Networks. The proposed method leverages a GCN architecture that integrates both local and global topological features through multi-hop message passing, enabling the extraction of expressive node embeddings that capture structural and behavioral distinctions between benign and Sybil nodes. To enhance performance, the model undergoes comprehensive hyper-parameter optimization, balancing detection accuracy with computational efficiency. The proposed approach is evaluated on a real-world Facebook follower-followee graph and achieves a high classification performance, significantly outperforming established baselines such as SybilGAT and SybilWalk. Notably, the model achieves an Area Under the Curve (AUC) of 96%, demonstrating its robustness and generalization capability for large-scale OSN environments.
References
- M. G. O. M. D. J. Thomas Aichner, "Twenty-Five Years of Social Media: A Review of Social Media Applications and Definitions from 1994 to 2019," CYBERPSYCHOLOGY, BEHAVIOR, AND SOCIAL NETWORKING, pp. 215-222, 2021.
- M. B. P. S. M. P. Heta Dasondi, "A Proposed Blockchain-Based Model for Online Social Network to Detect Suspicious Accounts," Singapore, 2023.
- J. R. Douceur, "The Sybil Attack," in Lecture Notes in Computer Science, Berlin, Heidelberg, 2002.
- H. X. M. L. H. H. S. Z. H. L. X. &. R. K. Zheng, "Smoke screener or straight shooter: Detecting elite sybil attacks in user-review social networks.," arXiv preprint arXiv:1709.06916., 2017.
- S. R. S. J. K. Ankit Kumar Jain, "Online social networks security and privacy: comprehensive review," Complex & Intelligent Systems, p. 2157–2177, 2021.
- B. Hogan, "Online Social Networks: Concepts for Data Collection and analysis," The Sage Handbook of Online Research Methods, Second edition, pp. 241-258, 2016.
- D.-A. S.-T. a. I.-S. M. Daniel Mican, "User Behavior on Online Social Networks: Relationships among Social Activities and Satisfaction," Symmetry, pp. 1-16, 2020.
- N. Z. F. M. &. M. P. Gong, "Sybilbelief: A semi-supervised learning approach for structure-based sybil detection.," IEEE transactions on information forensics and security, pp. 976-987, 2014.
- N. Z. G. a. H. F. Binghui Wang, "GANG: Detecting Fraudulent Users in Online Social Networks via Guilt-by-Association on Directed Graphs," IEEE International Conference on Data Mining (ICDM), 2017.
- Z. Y. a. Y. D. Y. Sun, "TrustGCN: Enabling Graph Convolutional Network for Robust Sybil Detection in OSNs," in IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), The Hague, Netherlands, 2020.
- X. L. ,. L. L. Jian Mao, "SybilHunter: Hybrid graph-based sybil detection by aggregating user behaviors," Neurocomputing, pp. 295-306, 2022.
- M. S. Y. P. Qiang Cao, "Aiding the detection of fake accounts in large scale social online services," in Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation, 2012.
- J. a. W. B. a. G. N. Z. Jia, "Random Walk Based Fake Account Detection in Online Social Networks," 2017 47th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), pp. 273-284, 2017.
- H. W. W. J. L. L. Shangbin Feng, "SATAR: A Self-supervised Approach to Twitter Account Representation Learning and its Application in Bot Detection," arXiv:2106.13089v4, 2021.
- D. G. L. L. L. Haoyu Lu, "SybilHP: Sybil Detection in Directed Social Networks with Adaptive Homophily Prediction," Applied Sciences., 2023.
- T. O. S. H. &. K. N. Talaei Khoei, "Deep learning: systematic review, models, challenges, and research directions," Neural Comput & Applic, p. 23103–23124, 2023.
- C. Y. B. P. K. R. Patel Devarshi, "A Comprehensive Deep Learning Model for Improved Person Re-identification Using Multi-Camera Streaming Pipeline," Procedia Computer Science, pp. 455-466, 2025.
- B. P. S. K. K. e. a. Khemani, "A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions," J Big Data, 2024.
- S. T. H. X. J. e. a. Zhang, "Graph convolutional networks: a comprehensive review," Comput Soc Netw, 2019.
- L. Z. a. N. Z. G. B. Wang, "SybilSCAR: Sybil detection in online social networks via local rule based propagation," IEEE INFOCOM 2017 - IEEE Conference on Computer Communications, pp. 1-9, 2017.
- ,. J. J. Z. Z. G. Binghui Wang, "Structure-based Sybil Detection in Social Networks via Local Rule-based Propagation," IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, no. arXiv:1803.04321v2, 2020.
- S. P. A. &. W. R. Heeb, "Sybil Detection using Graph Neural Networks," arXiv preprint arXiv:2409.08631, 202.
Index Terms
Keywords