Deepfake Detection System Integrating CNN in GAN for Social Media Platforms
C N Savithri, E Manjushree, E. Janani, Thiriphura Sundari C S · 2025
Deepfake technology has seen rapid growth which has raised significant concerns regarding privacy, security, and digital trust. Reports from 2023 indicate that over 500,000 deepfake videos and voice manipulations were identified, reflecting a 550% increase since 2019, with fraud cases surging tenfold between 2022 and 2023, emphasizing the urgent need for robust detection mechanisms. This paper introduces a hybrid detection framework that integrates Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) in a parallel processing setup. The CNN component extracts deep features, identifying pixel-level inconsistencies and texture irregularities, while GAN-based adversarial training improves the system's ability to distinguish synthetic content from real media. By operating in parallel, the two models complement each other, improving both efficiency and accuracy in deepfake detection. By mitigating the spread of manipulated digital content, this approach promotes responsible technology use and strengthens online security. The primary goal is to assist digital platforms, social media users, and organizations in combating misinformation and cyber fraud. By offering a reliable solution for deepfake identification and removal, this work contributes to fostering a safer and more trustworthy digital ecosystem.