Security analysis of the data of social networks using AI techniques
Keywords:
Social networks, , Security threats, Threat mitigation, Continuous monitoring, AUC-ROC, precision-recall curvesAbstract
This proposed research explores the potential of AI techniques, particularly user engagement prediction, for analyzing social network data and identifying potential security threats. Utilizing a Random Forest classifier, we developed a highly accurate model achieving 100% accuracy and a 1.0 AUC-ROC score. This exceptional performance demonstrates the ability of engagement prediction to accurately flag suspicious accounts with unusually low engagement, often associated with bots or fake profiles. Based on these findings, we implemented mitigation strategies such as flagging low-engagement accounts for further investigation and analyzing engagement trends to inform proactive security measures. Furthermore, our work opens doors for future research in combining engagement prediction with other AI techniques like sentiment analysis for even more sophisticated threat detection, ultimately contributing to the development of robust solutions for enhanced social network security and user privacy protection.
Downloads
References
Andrew, Reischer J., et al. "Systems and Methods for Identifying Safety and Security Threats in Social Media." (2019).
S, Jindal, and K. Sharma. "Intend to Analyze Social Media Feeds to Detect Behavioral Trends of Individuals to Proactively Act Against Social Threats." Procedia Computer Science, 2018 pp. 218-225.
Davis ,J., and J. Bekker. "Learning from Positive and Unlabeled Data: A Survey." Machine Learning, vol. 109, no. 4, 2020, pp. 719-760.
Alguliyev, R., et al. "MCDM Model for Evaluation of Social Network Security Threats." In "ECDG 2018," edited by R. Bouzas-Lorenzo and A. Cernadas Ramos, 2018, pp. 1-7.
M ,Sullivan, et al. "Social Media as a Data Resource for #MonkSeal Conservation." PLOS ONE, vol. 14, no. 10, (2019), "doi:10.1371/journal.pone.0222627".
Brown, R.C, et al. "Can Acute Suicidality Be Predicted by Instagram Data" PLOS ONE, 2019, doi:10.1371/journal.pone.0220623.
Kim, H., et al. "Predicting the Clinical Outcome of Cancer Patients." 2019.
Guacho, G. B., et al. "Semi-supervised Content-Based Detection of Misinformation." ASONAM 2018, pp. 322-325.
B, Bhutani., et al. "Fake News Detection Using Sentiment Analysis." 12th International Conference on Contemporary Computing (IC3), 2019, pp. 1-5.
Nugroho, K., et al. "Improving Random Forest Method to Detect Hatespeech and Offensive Word." International Conference on Information and Communication Technology (ICOIACT), 2019, pp. 514-518.
Machado, Gustavo, et al. "What variables are important in predicting bovine viral diarrhea virus? A random forest approach." Vet Res, vol. 46, 2015.
Ishaq, A. et al. "Improving the Prediction of Heart Failure Patients' Survival using SMOTE and Effective Data Mining Techniques." IEEE Access, 2021. doi: 10.1109/ACCESS.2021.3070755.
Zaki, Q., Kalbus, E., Khan, N., & Mohamed, M. M. "Utilization of social media in floods assessment using data mining techniques." PLOS ONE, 2022, doi:10.1371/journal.pone.0267079.
Purbay, M. & Kumar, D. "Split Behavior of Supervised Machine Learning Algorithms for Phishing URL Detection." Lecture Notes in Electrical Engineering, vol. 683, 2021.
Saad, Eysha, et al. "Novel Extreme Regression-Voting Classifier to Predict Death Risk in Vaccinated People Using VAERS Data." PLoS ONE, vol. 17, no. 6, 2022, p. e027032, doi:10.1371/journal.pone.0270327.
Tashtoush, Y., et al. "A Deep Learning Framework for Detection of COVID-19 Fake News on Social Media Platforms." Data, vol. 7, no. 5, May 13, 2022, pp. 65. https://doi.org/10.3390/data7050065.
Borkar, Bharat S. "Identification of Fake Identities on Social Media using various Machine Learning Algorithm." International Journal of Advanced Trends in Computer Science and Engineering, 2020.
Kumar, S., et al. "Fake News Detection Using Deep Learning Models: A Novel Approach." Transactions on Emerging Telecommunications Technologies, vol. 31, 2020, https://doi.org/10.1002/ett.3767.
Á. I. Rodríguez and L. L. Iglesias. "Fake News Detection using Deep Learning." arXiv, 2019. arXiv:1910.03496. Google Scholar.
Jiang, T., Li, J., Haq, A. U., & Saboor, A. (2020, December 18-20). Fake News Detection using Deep Recurrent Neural Networks. In Proceedings of the 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), Chengdu, China (pp. 205-208).
Umer, M., Imtiaz, Z., Ullah, S., Mehmood, A., Choi, G.S., and On, B.W. (2020). "Fake News Stance Detection using Deep Learning Architecture (CNN-LSTM)," IEEE Access, vol. 8, pp. 156695-156706.
X. Zhi, L. Xue, W. Zhi, Z. Li, B. Zhao, Y. Wang, and Z. Shen. "Financial Fake News Detection with Multi-Fact CNN-LSTM Model." Proceedings of the 2021 IEEE 4th International Conference on Electronics Technology, pp. 1338-1341, Chengdu, China, 7-10 May 2021.
Hakak, et al. "An Ensemble Machine Learning Approach." Future Generation Computer Systems 117 (2021): 47-58.
Wani, A. et al. "Evaluating deep learning approaches for COVID-19 fake news detection." International Workshop on Combating Online Hostile Posts, edited by Springer, 2021, pp. 153-163.
D.S., Ismail, F.H.., Nabil, A. "Coaiddeep: An optimized intelligent framework for automated detecting COVID-19 misleading information on twitter." IEEE Access, vol. 9, 2021, pp. 27840-27867.
Ajao, O., Bhowmik, D., & Zargari, S. "Fake News Identification on Twitter with Hybrid CNN and RNN Models." Proceedings of the 9th International Conference on Social Media and Society, 2018, pp. 226-230.
Nasir, J.A., Khan, O.S., Varlamis, I. "Fake news detection: A hybrid CNN-RNN based deep learning approach." International Journal of Information Management, Data Insights, vol. 1, 2021, 100007.
P., & Gill, S. Tackling COVID-19 infodemic using deep learning. In Lecture Notes on Data Engineering and Communications Technologies pp. 319-335. (2022).
Published
How to Cite
Issue
Section
Copyright (c) 2023 Journal of Applied Artificial Intelligence
This work is licensed under a Creative Commons Attribution 4.0 International License.
