An In-Depth Evaluation of Hybrid Approaches in Soft Computing for the Identification of Social Engineering

Abstract

Social engineering attacks continue to pose significant threats to information security by exploiting human psychology and manipulating individuals into divulging sensitive information or performing actions that compromise organizational systems. Traditional defense mechanisms often struggle to detect and mitigate such attacks due to their dynamic and deceptive nature. In response, the integration of hybrid soft computing techniques has developed as a promising method to enhance the accuracy and effectiveness of social engineering detection systems. This study provides an in-depth exploration of the various hybrid soft computing methodologies applied to the detection of social engineering attacks. It discusses the synergistic combination of different soft computing techniques, such as genetic algorithms, neural networks, swarm intelligence and fuzzy logic along with their integration with other security measures. The study presents a comprehensive survey of recent research advancements, methodologies, datasets, performance metrics, and challenges in the domain of hybrid soft computing for social engineering detection. Furthermore, it offers insights into potential future directions and applications for advancing the field.