Optimization of machine learning methods for de-anonymization in social networks
Nurzhigit Smailov
n.smailov@satbayev.universitySatbayev University, Department of Radio Engineering, Electronics and Space Technologies; Institute of Mechanics and Machine Science named by academician U.A. Dzholdasbekov (Kazakhstan)
Fatima Uralova
Al-Farabi Kazakh National University, Department of Cybersecurity and Cryptology; Almaty Academy of Ministry of Internal Affairs, Department of Cyber Security and Information Technology (Kazakhstan)
https://orcid.org/0009-0003-4159-2049
Rashida Kadyrova
Almaty Academy of Ministry of Internal Affairs, Department of Cyber Security and Information Technology (Kazakhstan)
Raiymbek Magazov
Al-Farabi Kazakh National University, Department of Artificial Intelligence and Big Data (Kazakhstan)
https://orcid.org/0009-0000-4105-2331
Akezhan Sabibolda
Satbayev University, Department of Radio Engineering, Electronics and Space Technologies; Institute of Mechanics and Machine Science named by academician U.A. Dzholdasbekov; Almaty Academy of Ministry of Internal Affairs, Department of Cyber Security and Information Technology (Kazakhstan)
https://orcid.org/0000-0002-1186-7940
Abstract
In recent years, social networks have struggled to meet user protection and fraud prevention requirements under unpredictable risks. Anonymity features are widely used to help individuals maintain their privacy, but they can also be exploited for malicious purposes. In this study, we develop a machine learning-driven de-anonymization system for social networks, with a focus on feature selection, hyperparameter tuning, and dimensionality reduction. Using supervised learning techniques, the system achieves high accuracy in identifying user identities from anonymized datasets. In experiments conducted on real and synthetic data, the optimized models consistently outperform baseline methods on average. Even in cases where they do not, significant improvements in precision are observed. Ethical considerations surrounding de-anonymization are thoroughly discussed, including the responsibility of implementation to maintain a balance between privacy and security. By proposing a scalable and effective framework for analyzing anonymized data in social networks, this research contributes to improved fraud detection and strengthened Internet security.
Keywords:
de-anonymization, social networks, machine learning, user privacy, data analysisReferences
[1] Abdykadyrov A. et al.: Optimization of Distributed Acoustic Sensors Based on Fiber Optic Technologies. Eastern-European Journal of Enterprise Technologies 5(131), 2024, 50–59 [https://doi.org/10.15587/1729-4061.2024.313455].
Google Scholar
[2] Fu X. et al.: De-Anonymization of Networks with Communities: When Quantifications Meet Algorithms. GLOBECOM 2017 – 2017 IEEE Global Communications Conference, Singapore 2017, 1–6 [https://doi.org/10.1109/glocom.2017.8254107].
Google Scholar
[3] Gao T., Li F.: De-Anonymizing Online Social Network with Conditional Generative Adversarial Network. 19th International Conference on Mobile Ad Hoc and Smart Systems (MASS), 2022, 496–504 [https://doi.org/10.1109/mass56207.2022.00076].
Google Scholar
[4] Jiang H. et al.: Structure-Attribute-Based Social Network Deanonymization with Spectral Graph Partitioning. IEEE Transactions on Computational Social Systems 9(3), 2021, 902–913 [https://doi.org/10.1109/tcss.2021.3082901].
Google Scholar
[5] Kuttybayeva A. et al.: Investigation of a Fiber Optic Laser Sensor with Grating Resonator Using Mirrors. Conference of Young Researchers in Electrical and Electronic Engineering (ElCon), IEEE, 2024, 709–711 [https://doi.org/10.1109/ElCon61730.2024.10468264].
Google Scholar
[6] Lee W.-H. et al.: Blind De-Anonymization Attacks Using Social Networks. arXiv (Cornell University), 2018 [https://doi.org/10.48550/arxiv.1801.05534].
Google Scholar
[7] Mao J. et al.: Understanding Structure-Based Social Network De-Anonymization Techniques via Empirical Analysis. EURASIP Journal on Wireless Communications and Networking 1, 2018 [https://doi.org/10.1186/s13638-018-1291-2].
Google Scholar
[8] Qian J. et al.: Social Network De-Anonymization and Privacy Inference with Knowledge Graph Model. IEEE Transactions on Dependable and Secure Computing 16(4), 2017, 679–692 [https://doi.org/10.1109/tdsc.2017.2697854].
Google Scholar
[9] Qian J. et al.: Social Network De-Anonymization: More Adversarial Knowledge, More Users Re-Identified? arXiv (Cornell University), 2017 [https://doi.org/10.48550/arxiv.1710.10998].
Google Scholar
[10] Rutba-Aman R. T., Rani Ghosh P.: Unveiling the Veiled: Leveraging Deep Learning and Network Analysis for De-Anonymization in Social Networks. J. of Primeasia 4(1), 2023, 1–6 [https://doi.org/10.25163/primeasia.4140042].
Google Scholar
[11] Sabibolda A. et al.: Estimation of the Time Efficiency of a Radio Direction Finder Operating on the Basis of a Searchless Spectral Method of Dispersion-Correlation Radio Direction Finding. Mechanisms and Machine Science 167, 2024, 62–70 [https://doi.org/10.1007/978-3-031-67569-0_8].
Google Scholar
[12] Shao Y. et al.: Fast De-Anonymization of Social Networks with Structural Information. Data Science and Engineering 4(1), 2019, 76–92 [https://doi.org/10.1007/s41019-019-0086-8].
Google Scholar
[13] Smailov N. et al.: Approaches to Evaluating the Quality of Masking Noise Interference. International Journal of Electronics and Telecommunications 67(1), 2020, 59–64 [https://doi.org/10.24425/ijet.2021.135944].
Google Scholar
[14] Smailov N. et al.: Streamlining Digital Correlation-Interferometric Direction Finding with Spatial Analytical Signal. Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska 14(3), 2024, 43–48 [https://doi.org/10.35784/iapgos.6177].
Google Scholar
[15] Tereikovskyi I. et al.: Method for Constructing Neural Network Means for Recognizing Scenes of Political Extremism in Graphic Materials of Online Social Networks. International Journal of Computer Network and Information Security 16(3), 2024, 52–69 [https://doi.org/10.5815/ijcnis.2024.03.05].
Google Scholar
Authors
Nurzhigit Smailovn.smailov@satbayev.university
Satbayev University, Department of Radio Engineering, Electronics and Space Technologies; Institute of Mechanics and Machine Science named by academician U.A. Dzholdasbekov Kazakhstan
Authors
Fatima UralovaAl-Farabi Kazakh National University, Department of Cybersecurity and Cryptology; Almaty Academy of Ministry of Internal Affairs, Department of Cyber Security and Information Technology Kazakhstan
https://orcid.org/0009-0003-4159-2049
Authors
Rashida KadyrovaAlmaty Academy of Ministry of Internal Affairs, Department of Cyber Security and Information Technology Kazakhstan
Authors
Raiymbek MagazovAl-Farabi Kazakh National University, Department of Artificial Intelligence and Big Data Kazakhstan
https://orcid.org/0009-0000-4105-2331
Authors
Akezhan SabiboldaSatbayev University, Department of Radio Engineering, Electronics and Space Technologies; Institute of Mechanics and Machine Science named by academician U.A. Dzholdasbekov; Almaty Academy of Ministry of Internal Affairs, Department of Cyber Security and Information Technology Kazakhstan
https://orcid.org/0000-0002-1186-7940
Statistics
Abstract views: 53PDF downloads: 30
Most read articles by the same author(s)
- Nurzhigit Smailov, Vitaliy Tsyporenko, Akezhan Sabibolda, Valentyn Tsyporenko, Askar Abdykadyrov, Assem Kabdoldina, Zhandos Dosbayev, Zhomart Ualiyev, Rashida Kadyrova, STREAMLINING DIGITAL CORRELATION-INTERFEROMETRIC DIRECTION FINDING WITH SPATIAL ANALYTICAL SIGNAL , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 14 No. 3 (2024)
- Sunggat Marxuly, Askar Abdykadyrov, Katipa Chezhimbayeva, Nurzhigit Smailov, STUDY OF THE OZONE CONTROL PROCESS USING ELECTRONIC SENSORS , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 14 No. 4 (2024)
