Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
We survey deepfake generation and detection techniques, covering all deepfake media types: image, video, audio and multimodal content. We identify various kinds of deepfakes and construct taxonomies of deepfake generation and detection methods, illustrating the important groups of methods. Next, we gather datasets used for deepfake detection and provide updated rankings of the best performing detectors on the most popular datasets. In addition, we develop a novel multimodal benchmark to evaluate deepfake detectors on out-of-distribution content. The results indicate that state-of-the-art detectors fail to generalize to deepfakes generated by unseen generators. Our project page and new benchmark are available at https://github.com/CroitoruAlin/biodeep.
Authors
- Florinel-Alin Croitoru (ORCID: https://orcid.org/0009-0002-4187-4102)
- Nicolae Catalin Ristea
- Paul Irofti (ORCID: https://orcid.org/0000-0002-7541-4334)
- Cristian Rusu (ORCID: https://orcid.org/0000-0002-7165-1543)
- Vlad Hondru (ORCID: https://orcid.org/0009-0003-8074-6266)
- Radu Tudor Ionescu (ORCID: https://orcid.org/0000-0002-9301-1950)
- Marius Popescu (ORCID: https://orcid.org/0000-0003-4158-3911)
- Fahad Shahbaz Khan (ORCID: https://orcid.org/0000-0002-4263-3143)
- Mubarak Shah (ORCID: https://orcid.org/0000-0002-8216-1128)
- Andrei-Iulian Hiji
Institutions
- University of Central Florida (US)
- University of Bucharest (RO)
- Mohamed bin Zayed University of Artificial Intelligence (AE)
Publication Details
- Journal
- ACM Computing Surveys
- Published
- 2026-07-23
- DOI
- https://doi.org/10.1145/3833867
- Citations
- 2
- Primary Topic
- Generative Adversarial Networks and Image Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 7.09