A Study on Deepfake Detection with Continual Learning

DOI

10.2991/978-94-6239-610-4_31How to use a DOI?

Keywords

Continual Learning; Catastrophic Forgetting; Deepfake Detection; Generative Models; Multi-modal Analysis; Prompt-based Optimization

Abstract

The rapid advancement of deepfake technology has made it increasingly challenging to distinguish between real and manipulated digital content, raising significant concerns for public trust, privacy, and security. While detection methods have progressed to identify forgeries generated by GANs and diffusion models, most approaches rely on static and homogeneous training data, which does not reflect the evolving landscape of deepfake generation. Although several review studies exist, there is no comprehensive survey providing a systematic overview with unified evaluation metrics. Continual deepfake detection, which aims to adapt to new manipulations without forgetting previously learned knowledge, has received limited attention and faces challenges such as taskidentification dependencies and computational overhead. This survey consolidates existing research on detection methods, continual learning strategies, datasets, and associated challenges. It provides a taxonomy of approaches and highlights open problems to guide the development of robust, adaptable, and future-proof deepfake detection systems.

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  - Nekkanti Mownika
AU  - N. Swapna Goud
AU  - Y. V. R. Naga Pawan
PY  - 2026
DA  - 2026/05/05
TI  - A Study on Deepfake Detection with Continual Learning
BT  - Proceedings of the First International Conference on Advances in Forensics and Cyber Technologies (ICFACT 2025)
PB  - Atlantis Press
SP  - 352
EP  - 372
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-610-4_31
DO  - 10.2991/978-94-6239-610-4_31
ID  - Mownika2026
ER  -