Temporal Drift Modeling in Multimodal Frameworks for Sockpuppet Detection in Social Networks: A Theoretical Framework
DOI:
https://doi.org/10.54536/ajiri.v5i3.8282Keywords:
Late Fusion, Multimodal Ai, Privacy-Preserving Ai, Social Network Security, Sockpuppet Detection, Temporal DriftAbstract
Sockpuppet accounts, multiple fake profiles controlled by a single operator, threaten the integrity of online social networks through coordinated disinformation and opinion manipulation. Existing detection methods rely on static snapshots of behavioral or textual features, leaving them blind to a defining sockpuppet characteristic: deliberate dormancy followed by coordinated reactivation. This paper proposes a four-modality late-fusion framework that extends the multimodal deduplication architecture into the social network domain. Three existing modalities, semantic text embeddings, static behavioral features, and device metadata, are adapted for the social network context. A fourth modality, Temporal Drift, is formally introduced, defined through the Activity Window, Baseline Profile, Drift Vector, Temporal Drift Score (TDS), Dormancy Threshold, and Burst Index. Grounded in time-series anomaly theory, the framework detects dormancy-to-activation behavioral signatures without relying on any personally identifiable information (PII). Building on an expanded review of the 2022–2026 literature on coordinated inauthentic behavior, sybil detection, concept drift, and trustworthy AI, a theoretical comparison with four prior works confirms the framework’s unique position as, to the authors’ knowledge, the only approach combining multimodal fusion, temporal drift sensitivity, privacy preservation, social network applicability, and unsupervised operation. Beyond cybersecurity, the framework contributes to trustworthy AI, privacy-preserving behavioral analytics, and interdisciplinary digital identity research
Downloads
References
Agarwal, P., Manekiya, M., Ahmad, T., Yadav, A., Kumar, A., Donelli, M., & Mishra, S. T. (2022). A survey on Citizens Broadband Radio Service (CBRS). Electronics, 11(23), 3985. https://doi.org/10.3390/electronics11233985
Ahmed, M. O. S. (2025). A Late-Fusion Multimodal AI Framework for Privacy-Preserving Deduplication in National Healthcare Data Environments. 2025 IEEE FMLDS
Alharbi, A., Dong, H., Yi, X., Tari, Z., & Khalil, I. (2021). Social Media Identity Deception Detection. ACM Computing Surveys, 54(3), 1-35. https://doi.org/10.1145/3446372
Aljabri, M., Zagrouba, R., Shaahid, A., Alnasser, F., Saleh, A., & Alomari, D. M. (2023). Machine learning-based social media bot detection: A comprehensive literature review. Social Network Analysis and Mining, 13(1). https://doi.org/10.1007/s13278-022-01020-3
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82-115. https://doi.org/10.1016/j.inffus.2019.12.012
Bellutta, D., & Carley, K. M. (2023). Investigating coordinated account creation using burst detection and network analysis. J Big Data, 10(1), 20. https://doi.org/10.1186/s40537-023-00695-7
Breuer, A., Khosravani, N., Tingley, M., & Cottel, B. (2023). Preemptive detection of fake accounts on social networks via multi-class preferential attachment classifiers. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’23).
Chamola, V., Hassija, V., Sulthana, A. R., Ghosh, D., Dhingra, D., & Sikdar, B. (2023). A Review of Trustworthy and Explainable Artificial Intelligence (XAI). IEEE Access, 11, 78994-79015. https://doi.org/10.1109/access.2023.3294569
Cima, L., Mannocci, L., Avvenuti, M., Tesconi, M., & Cresci, S. (2024). Coordinated behavior in information operations on Twitter. IEEE Access, 11, 61568-61585.
Cinelli, M., Cresci, S., Quattrociocchi, W., Tesconi, M., & Zola, P. (2022). Coordinated inauthentic behavior and information spreading on Twitter. Decision Support Systems, 160. https://doi.org/10.1016/j.dss.2022.113819
Cinus, F., Minici, M., Luceri, L., & Ferrara, E. (2024). Exposing Cross-Platform Coordinated Inauthentic Activity in the Run-Up to the 2024 U.S. Election. https://arxiv.org/abs/2410.22716
Ding, C., Zhao, J., & Sun, S. (2022). Concept Drift Adaptation for Time Series Anomaly Detection via Transformer. Neural Processing Letters, 55(3), 2081-2101. https://doi.org/10.1007/s11063-022-11015-0
Doshi, J., Novacic, I., Fletcher, C., Borges, M., Zhong, E., Marino, M. C., Gan, J., Mager, S., Sprague, D., & Xia, M. (2024). Sleeper Social Bots: A New Generation of AI Disinformation Bots are Already a Political Threat. https://arxiv.org/abs/2408.12603
Fu, D., He, J., Tong, H., & Maciejewski, R. (2022). Privacy-Preserving Graph Analytics: Secure Generation and Federated Learning. https://arxiv.org/abs/2207.00048
Goyal, B., Gill, N. S., Gulia, P., Prakash, O., Priyadarshini, I., Sharma, R., Obaid, A. J., & Yadav, K. (2023). Detection of Fake Accounts on Social Media Using Multimodal Data with Deep Learning. IEEE Transactions on Computational Social Systems.
Gruzd, A., Soares, F. B., & Mai, P. (2023). Trust and Safety on Social Media: Understanding the Impact of Anti-Social Behavior and Misinformation on Content Moderation and Platform Governance. Social Media + Society, 9(3). https://doi.org/10.1177/20563051231196878
Heeb, S., & Plesner, A. (2024). Sybil Detection using Graph Neural Networks. https://arxiv.org/abs/2409.08631
Jiang, H., Pei, J., Yu, D., Yu, J., Gong, B., & Cheng, X. (2023). Applications of Differential Privacy in Social Network Analysis: A Survey. IEEE Transactions on Knowledge and Data Engineering, 35(1), 108-127.
Kaur, D., Uslu, S., Rittichier, K. J., & Durresi, A. (2022). Trustworthy Artificial Intelligence: A Review. ACM Computing Surveys, 55(2), 1-38. https://doi.org/10.1145/3491209
Khaliq, A. R., Ullah, S., Ahmad, T., Yadav, A., & Majid, M. I. (2023). Behavioral analysis of backdoor malware exploiting heap overflow vulnerabilities using data mining and machine learning. Pakistan Journal of Engineering, Technology & Science, 11(1). https://doi.org/10.22555/pjets.v11i1.984
Khan, Z., Khan, Z., Lee, B.-G., Kim, H. K., & Jeon, M. (2024). Graph neural networks based framework to analyze social media platforms for malicious user detection. Applied Soft Computing, 155. https://doi.org/10.1016/j.asoc.2024.111416
Lazebnik, T., & Iny, O. (2024). Temporal graphs anomaly emergence detection: benchmarking for social media interactions. Applied Intelligence, 54(23), 12347-12356. https://doi.org/10.1007/s10489-024-05821-3
Li, J., Malialis, K., & Polycarpou, M. M. (2023). Autoencoder-based Anomaly Detection in Streaming Data with Incremental Learning and Concept Drift Adaptation (strAEm++DD). https://arxiv.org/abs/2305.08977
Li, Y. (2024). Malicious Social Bot Detection in Social Networks Based on Multi-modal Feature Fusion with Transformer Networks. ACM CSCIT,
Liu, J., Yang, D., Zhang, K., Gao, H., & Li, J. (2023). Anomaly and change point detection for time series with concept drift. World Wide Web, 26(5), 3229-3252. https://doi.org/10.1007/s11280-023-01181-z
Lu, H., Gong, D., Li, Z., Liu, F., & Liu, F. (2023). SybilHP: Sybil Detection in Directed Social Networks with Adaptive Homophily Prediction. Applied Sciences, 13(9). https://doi.org/10.3390/app13095341
Luceri, L., Salkar, T. V., & Balasubramanian, A. (2025). Coordinated Inauthentic Behavior on TikTok: Challenges and Opportunities for Detection in a Video-First Ecosystem. https://arxiv.org/abs/2505.10867
Manekiya, M., Kumar, A., Yadav, A., & Donelli, M. (2020). A survey of resource allocation techniques for cellular network’s operation in the unlicensed band. Electronics, 9(9), 1464. https://doi.org/10.3390/electronics9091464
Mannocci, L. (2025). Conceptual Framework and Methods for the Analysis of Coordinated Online Behavior National PhD Program in AI for Society]. Pisa, Italy.
Mannocci, L., Mazza, M., Monreale, A., Vakali, A., & Tesconi, M. (2024). Detection and Characterization of Coordinated Online Behavior: A Survey. https://arxiv.org/abs/2408.01257
Moore, M. (2023). Fake accounts on social media, epistemic uncertainty and the need for an independent auditing of accounts. Internet Policy Review, 12(1).
Paganelli, M., Buono, F. D., Baraldi, A., & Guerra, F. (2022). Analyzing how BERT performs entity matching. Proceedings of the VLDB Endowment, 15(8), 1726-1738. https://doi.org/10.14778/3529337.3529356
Saeed, W., & Omlin, C. (2023). Explainable AI (XAI): A systematic meta-survey of current challenges and future opportunities. Knowledge-Based Systems, 263. https://doi.org/10.1016/j.knosys.2023.110273
Saha, S., Ahmad, T., & Yadav, A. (2025). Miscellaneous applications of deep learning based multi-sensor Earth observation. In S. Saha (Ed.), Deep learning for multi-sensor Earth observation (Chapter 15). Elsevier.
Sunkara, S. P. (2026a). AI-Enabled Drone Image Analysis Workflows for Condition Monitoring of Power Distribution Assets. 2026 International Symposium of Systems, Advanced Technologies and Knowledge (ISSATK), Hammamet, Tunisia, 1–6. https://doi.org/10.1109/ISSATK69667.2026.11566851
Sunkara, S. P. (2026b). Enhancing Grid Stability with AI-Driven Control Systems. 2026 International Symposium of Systems, Advanced Technologies and Knowledge (ISSATK), Hammamet, Tunisia. https://doi.org/10.1109/ISSATK69667.2026.11566761
Sunkara, S. P. (2026c). Physics-Informed AI Digital Twins For Ultra-Fast, Scalable Time-Series Power Flow And Automated Grid Constraint Resolution. International Journal of Advances in Signal and Image Sciences, 12(3s), 356–377. https://doi.org/10.29284/ecrg7s57
Sunkara, S. P., & Sunkara, K. (2026). Digital Twin–Enabled Grid Resilience: Predictive Failure Analysis and Proactive Control for Climate-Driven Power System. International Journal of Computer Information Systems and Industrial Management Applications, 18(1s), 479–491. https://doi.org/10.70917/ijcisim-2026-1940
Thiebes, S., Lins, S., & Sunyaev, A. (2020). Trustworthy artificial intelligence. Electronic Markets, 31(2), 447-464. https://doi.org/10.1007/s12525-020-00441-4
Tsikerdekis, M., & Zeadally, S. (2014). Multiple Account Identity Deception Detection in Social Media Using Nonverbal Behavior. IEEE Transactions on Information Forensics and Security, 9(8), 1311-1321. https://doi.org/10.1109/TIFS.2014.2325052
Xiang, Q., Zi, L., Cong, X., & Wang, Y. (2023). Concept Drift Adaptation Methods under the Deep Learning Framework: A Literature Review. Applied Sciences, 13(11). https://doi.org/10.3390/app13116515
Yadav, A., Manekiya, M., Ahmad, T., & Khan, M. A. (2023). Adopting sustainable agriculture practices in developing nations using CBRS. 2023 IEEE 8th International Conference on Engineering Technologies and Applied Sciences (ICETAS).
Yang, W., Wei, Y., & Wei, H. (2023). Survey on explainable AI: From approaches, limitations and applications aspects. Human-Centric Intelligent Systems, 3, 161-188.
Zamanzadeh Darban, Z., Webb, G. I., Pan, S., Aggarwal, C., & Salehi, M. (2024). Deep Learning for Time Series Anomaly Detection: A Survey. ACM Computing Surveys, 57(1), 1-42. https://doi.org/10.1145/3691338
Zhong, C., & Goel, S. (2024). Transparent AI in Auditing through Explainable AI. Current Issues in Auditing, 18(2), A1-A14. https://doi.org/10.2308/ciia-2023-009
Zhu, J., Cai, S., Deng, F., Ooi, B. C., & Zhang, W. (2023). METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection. https://arxiv.org/abs/2312.16831
Zouzou, Y., & Varol, O. (2024). Unsupervised detection of coordinated fake-follower campaigns on social media. EPJ Data Science, 13.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mohammed Mhothasim Ali
This work is licensed under a Creative Commons Attribution 4.0 International License.
