Deepfake Video Detection: How Far Have We Gone?

Kotevski, Zoran (2025) Deepfake Video Detection: How Far Have We Gone? In: XV International Conference on Applied Internet and Information Technologies (AIIT 2025), 7 November 2025, Bitola, Macedonia.

Text Paper AIIT2025 - Zoran Kotevski.pdf - Published Version Download (1MB)

Abstract

The increasing sophistication and accessibility of Deepfake technology, which leverages advanced deep learning models to create realistic manipulated videos, poses a significant and escalating threat to information integrity, personal privacy, and public discourse. We may already be at a point where Deepfake videos are indiscernible from real, and in recent years we witness extensive efforts to develop robust and generalizable Deepfake detection methods. This research provides a review of the latest Deepfake video detection models and architectures, and discusses the key technical aspects that are still considered under-researched or represent major open challenges in this field.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Scientific Fields (Frascati) > Natural sciences > Computer and information sciences Scientific Fields (Frascati) > Engineering and Technology > Electrical engineering, electronic engineering,information engineering
Divisions:	Faculty of Information and Communication Technologies
Depositing User:	Prof. d-r. Zoran Kotevski
Date Deposited:	10 Dec 2025 10:21
Last Modified:	10 Dec 2025 10:21
URI:	https://eprints.uklo.edu.mk/id/eprint/11264

Actions (login required)

View Item