Book Title: Shaping the Future: Innovation, Sustainability, and Inclusive Growth in a Globalized Economy
Editors: Editors: Dr. Shanu Singh, and Dr. Yashmita Awasthi
Student Editor: Krishna Singh Rawat
ISBN: 978-93-7183-006-5
Chapter: 4
DOI: https://doi.org/10.59646/725/4
Authors: Jyotirmayee Sahoo, S. Chanti, and Jossy George
Abstract
The Artificial Intelligence is advancing rapidly with GAN-based techniques that create realistic synthetic media, often referred to as deepfakes, in which the facial features of individuals are manipulated to appear authentic (Rana, 2024; Mathew & Rodas, 2024). Deepfakes come with both advantages and disadvantages, as it is helpful in movies and gaming but can also cause serious problems if misused (Lim et al., 2024; Li et al., 2016). One of the biggest problems in recent times is the deepfake phishing, where the attackers combine real and fake videos which appears more authentic unlike traditional phishing which uses the fake emails and messages (Afchar et al., 2018; Ma et al., 2024). The attackers use these fake videos to deceive users and extract credentials (ATM PINs, passwords) which eventually lead to significant financial losses (Mathew & Rodas, 2024). Even though the detection of the deepfake has been a leading research area (He et al., 2016; Babaei et al., 2025), the existing algorithmic methods to detect deepfake reveal specific limitations when these methods are tested on various scenarios.