Deep Learning-Based Speech and Vision Synthesis to Improve Phishing Attack Detection through a Multi-layer Adaptive Framework
This work addresses the challenge of improving phishing attack detection for cybersecurity researchers and practitioners, though it appears incremental as it builds on existing methods like deep learning and random forest.
The authors tackled the problem of detecting complex phishing attacks by proposing an adaptable framework that combines deep learning and random forest to analyze images, synthesize speech from deep-fake videos, and use natural language processing across multiple layers, resulting in a significant performance increase for machine learning models in phishing detection.
The ever-evolving ways attacker continues to im prove their phishing techniques to bypass existing state-of-the-art phishing detection methods pose a mountain of challenges to researchers in both industry and academia research due to the inability of current approaches to detect complex phishing attack. Thus, current anti-phishing methods remain vulnerable to complex phishing because of the increasingly sophistication tactics adopted by attacker coupled with the rate at which new tactics are being developed to evade detection. In this research, we proposed an adaptable framework that combines Deep learning and Randon Forest to read images, synthesize speech from deep-fake videos, and natural language processing at various predictions layered to significantly increase the performance of machine learning models for phishing attack detection.