Deep Learning-Based Speech and Vision Synthesis to Improve Phishing Attack Detection through a Multi-layer Adaptive Framework

TL;DR

This paper introduces a multi-layer adaptive framework combining deep learning and random forest techniques to enhance phishing attack detection by analyzing images, speech, and text, addressing the challenge of evolving attack methods.

Contribution

The novel framework integrates deep learning with random forest to improve detection of complex phishing attacks across multiple data modalities.

Findings

Enhanced detection accuracy for sophisticated phishing attacks

Effective synthesis of speech and image analysis for phishing detection

Improved robustness over traditional single-method approaches

Abstract

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.