Building and Evaluating an Annotated Corpus for Automated Recognition of Chat-Based Social Engineering Attacks

Chat-based Social Engineering (CSE) is widely recognized as a key factor to successful cyber-attacks, especially in small and medium-sized enterprise (SME) environments. Despite the interest preventing CSE attacks, few studies have considered specific features of language used by attackers. This work contributes area early-stage automated attack recognition proposing an approach for building annotating specific-purpose corpus presenting its application domain. The resulting then evaluated training bi-directional long short-term memory (bi-LSTM) neural network purpose named entity (NER). results this study emphasize importance adding plethora metadata dataset provide critical in-context produce that broadens our understanding tactics social engineers. outcomes can be applied dedicated cyber-defence mechanisms utilized protect SME employees using Electronic Medium Communication (EMC) software.