Analyzing Adversarial Strategies and Countermeasures for Cyberbullying Detection
Published in International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS 2025), 2025
This study examines the resilience of text-based cyberbullying detection models against word-level and character-level adversarial attacks, comparing traditional ML and LLM-based approaches such as CyberBERT.
Recommended citation: Juarez, M., Abdukhamidov, E., Sandoval, M., Nazari, M., Hall, D., Thiruvathukal, G. K., Abuhmed, T., Silva, Y. N., & Abuhamad, M. (2025). Analyzing Adversarial Strategies and Countermeasures for Cyberbullying Detection. In Proceedings of the International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation (pp. 86–95). Springer Nature Switzerland.
Download Paper