Detection of Multimodal Deepfake: Datasets, Evaluation Metrics, and Approaches

DOI

10.2991/978-94-6239-727-9_14How to use a DOI?

Keywords

Deepfake Detection; CNN; RNN; Hybrid Model; ViT Model

Abstract

Manipulated multimedia is a critical challenge in our day to day life. In the preceding decades, rapid progress in Artificial Intelligence, Machine Learning, and Deep Learning has resulted in new techniques and various tools for altering media formats. Advanced AI tools are used to produce fabricated videos, false images, tampered audio or staged audio-visual recordings. Altered multimedia’s ability to appear and sound authentic makes them particularly unsafe. These are simply “deepfakes”. Detecting these deepfakes is challenging because they are often multimodal, integrating inconsistent data sources such as video, audio, and text. This paper explores a survey of the main research in multimodal deepfake detection. In this work, we present a systematic analysis of the representative datasets and evaluation metrics used in the field, followed by a taxonomy of different deepfake detection approaches. We also compare the strengths and weaknesses of DL deepfake detection approaches. Finally, we discuss the challenges researchers face and suggest future directions to make detection systems more reliable and effective.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, 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 changes were made.

Download article (PDF)

TY  - CONF
AU  - Sampada Aditya Kulkarni
AU  - Pooja Sapra
PY  - 2026
DA  - 2026/07/22
TI  - Detection of Multimodal Deepfake: Datasets, Evaluation Metrics, and Approaches
BT  - Proceedings of the International Conference on Sustainable Micro-Nano Materials & Innovative Technology (ICSUMMIT 2026)
PB  - Atlantis Press
SP  - 180
EP  - 205
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-727-9_14
DO  - 10.2991/978-94-6239-727-9_14
ID  - Kulkarni2026
ER  -