Advancements and Challenges in Deepfake Detection Using Deep Learning Approaches

DOI

10.2991/978-94-6239-768-2_16How to use a DOI?

Keywords

Deep Learning; Deepfake Detection; Convolutional Neural Networks (CNN); Generative Adversarial Networks (GAN); Multimedia Forensics; Systematic Review; Generalization; Robustness; Interpretability

Abstract

The advent of advanced deepfake technology, driven by DL breakthroughs, is threatening privacy of individuals, social trust, and national security. Deepfakes are super-realistic fake media created using algorithms such as Generative Adversarial Networks (GANs) and autoencoders that can convincingly reproduce human likeness and voice, making it incredibly hard to detect manually. Automated detection techniques, especially those relying on DL, have thus become indispensable. This article summarizes the state-of-the-art in DL-based deepfake detection and draws heavily upon the systematic review published by Heidari et al. We summarize deepfake generation methods and group existing detection methods according to the target modality: image, video, audio, and hybrid multimedia. The analysis emphasizes the dominance of Convolutional Neural Networks (CNNs) and the focus on video deepfakes by the research community. Much work notwithstanding, key limitations include weak generalization over disparate datasets, low robustness towards realistic distortions, weak model interpretability, and heavy computational requirements. Based on these gaps, this paper describes key research frontiers and suggests a future research agenda for developing more consistent, robust, efficient, and generalizable deepfake detectors.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits any noncommercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if you modified the licensed material. You do not have permission under this license to share adapted material derived from this chapter or parts of it.

Download article (PDF)

TY  - CONF
AU  - Yasir Afaq
AU  - Hashim Zahoor
AU  - Kashish
AU  - Rohit Kumar Gond
AU  - Mohan Kumar Jena
AU  - Mukesh Kumar
PY  - 2026
DA  - 2026/09/07
TI  - Advancements and Challenges in Deepfake Detection Using Deep Learning Approaches
BT  - Proceedings of the Third International Conference on Recent Advances in Computing Sciences (RACS 2025)
PB  - Atlantis Press
SP  - 152
EP  - 162
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-768-2_16
DO  - 10.2991/978-94-6239-768-2_16
ID  - Afaq2026
ER  -