Modeling Coherency in Generated Emails by Leveraging Deep Neural Learners
This work addresses the challenge of automatic text generation for targeted email attacks, which is an incremental improvement in a domain-specific area of cybersecurity.
The paper tackles the problem of generating coherent and contextually appropriate emails for social engineering attacks by using a hierarchical deep neural model, resulting in synthesized text evaluated through both qualitative and quantitative measures.
Advanced machine learning and natural language techniques enable attackers to launch sophisticated and targeted social engineering-based attacks. To counter the active attacker issue, researchers have since resorted to proactive methods of detection. Email masquerading using targeted emails to fool the victim is an advanced attack method. However automatic text generation requires controlling the context and coherency of the generated content, which has been identified as an increasingly difficult problem. The method used leverages a hierarchical deep neural model which uses a learned representation of the sentences in the input document to generate structured written emails. We demonstrate the generation of short and targeted text messages using the deep model. The global coherency of the synthesized text is evaluated using a qualitative study as well as multiple quantitative measures.