Cyberbullying are becoming more susceptible to online social networks because of the large-scale user generated content. The current methods of detection are primarily post-event methods and lack built-in prevention strategies, thereby limiting their ability to ensure the protection of user privacy and platform security. In this paper, a Horned Lizard CatBoost Framework (HLCF) is proposed to predict and prevent cyber threats active in social networks in advance. It uses the Horned Lizard Optimisation of adaptive feature selection with a CatBoost-based classifier to precisely differentiate between malicious and non malicious activity. The existing approaches lack methods that combine feature selection with optimisation, and a preventive mechanism for access-control. The framework was tested with benchmark social media datasets, which comprised over 47000 instances, and cross-validation and standard train test splits. The findings indicate that optimised threat prediction gained 99.98% accuracy prediction, 99.98% precision, 99.98% recall, and a 99.98% F1score. Meanwhile, it reduced the error ratio by 0.0001%. . The suggested HLCF provides a scalable solution for improving security and privacy. This work demonstrates the efficiency of combining bio-inspired optimisation with machine learning for cyberbullying prevention in social networks.
Hilal A, Kumar S, Patel D. Session-aware deep learning for social media cyber threat detection. Computers & Security. 2025;103952.
2.
Gaur V, Singh P, Bansal A. Multimodal deep neural models for detecting abusive and toxic social media content. IEEE Trans Comput Soc Syst. 2024;(2):224–36.
3.
Alsharif M, Logeshwaran T. Transformer-based hybrid architectures for online social network threat detection. Neural Computing and Applications. 2024;21845–60.
4.
Khan I, Ahmad Z. Deep sequential attention networks for detecting coordinated cyberbullying on social media. IEEE Transactions on Knowledge and Data Engineering. 2025;(1):45–58.
5.
Zheng W, Xu J. Bot and fake account detection through dynamic graph neural networks. IEEE Transactions on Knowledge and Data Engineering. 2024;(2):765–78.
6.
Aura J, Basso F. Ethical challenges and detection of misinformation in digital ecosystems. Technological Forecasting and Social Change. 2023;122637.
7.
Apruzzese G, Colajanni M. Adversarial robustness of machine learning in social network security applications. Computers & Security. 2023;103076.
8.
Uchendu D, Tiwari S. Bio-inspired optimisation techniques for neural model tuning in cybersecurity applications. IEEE Access. 2025;11294–310.
Bharadiya M, Shah A. A hybrid CatBoost-metaheuristic model for intelligent cyber-attack detection. Expert Systems with Applications. 2024;121474.
11.
Adebukola R, Lin Z. Intelligent cyber-attack mitigation using optimised ensemble learning. Knowledge-Based Systems. 2023;111279.
12.
Mengash H, Gull S. User-centric multi-factor authentication schemes for digital ecosystems. IEEE Access. 2023;75016–29.
13.
Sharma P, Rao K. Privacy and legal implications of national identity integration in online authentication. Computer Law & Security Review. 2023;105884.
14.
Chen X, Zhang L. Trust-aware adaptive security frameworks for social network access control. Information Sciences. 2025;120099.
15.
Li H, Dong Y. Metaheuristic tuning of gradient boosting models for cybersecurity datasets. Applied Intelligence. 2025;13548–64.
16.
Lin CJ, Chen BH, Lin CH, Jhang JY. Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle Recognition. Mathematics. 2024;12(24):3885.
17.
Saini H, Mehra H, Rani R, Jaiswal G, Sharma A, Dev A. Enhancing cyberbullying detection: a comparative study of ensemble CNN–SVM and BERT models. Social Network Analysis and Mining. 2023;14(1).
18.
Gutiérrez-Batista K, Gómez-Sánchez J, Fernandez-Basso C. Improving automatic cyberbullying detection in social network environments by fine-tuning a pre-trained sentence transformer language model. Social Network Analysis and Mining. 2024;14(1).
19.
Agushaka J, Ezugwu A, Abualigah L. A multi-strategy Horned Lizard Optimisation algorithm for complex optimisation and advanced feature selection problems. Journal of Big Data. 2025;(1):107.
20.
Khan M, Rehman M, Akhtar N. Comparative analysis of CatBoost, LightGBM, XGBoost, RF, and DT methods optimised with PSO for intrusion detection in wireless sensor networks. International Journal of Machine Learning and Cybernetics. 2025;
21.
Saeed A, Rahman M. Zero-trust authentication for online social platforms using secure token exchange. Journal of Network and Computer Applications. 2024;103680.
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.
,
