Deep Learning Approaches for Cyber Threat Detection and Mitigation.

Cyberspace has inflated over the past decade, primarily driven by pervasive development and widespread usage of the internet. Prolonged cyber-attacks and security vulnerabilities have become more common as a consequence. A recent study conducted by Ponemon Institute revealed that 64% of businesses have suffered web-based attacks in 2023. Thus, cybersecurity measures have become mandatory in every sector, that leverages technology, to protect confidential information from malignant threats. The majority of the sectors use conventional security measures like anti-virus products to defend their systems against outside attacks, however, these products fail to work on unseen and polymorphic threats. With cutting-edge deep learning (DL) processes getting adopted in nearly every field, it has been widely exploited in cybersecurity to detect and classify cyber-attacks. This study discusses the application of common deep learning models in cybersecurity to detect malware, intrusion, phishes, and spam. This study provides a description of deep learning models and their mathematical backgrounds that are common in cybersecurity. This study also reviews and analyses the work of other researchers who experimented with deep learning models in cybersecurity. This study delineates the challenges faced by deep learning models in cybersecurity. Finally, concluding remarks and future research directions are summarized to foresee the potential improvement of deep learning in cybersecurity.