Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook

[Submitted on 29 Nov 2024 (v1), last revised 23 Jul 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract: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 this https URL.

Submission history

From: Radu Tudor Ionescu [view email]
[v1] Fri, 29 Nov 2024 08:29:25 UTC (45,220 KB)
[v2] Thu, 25 Jun 2026 21:42:53 UTC (38,454 KB)
[v3] Thu, 23 Jul 2026 12:41:39 UTC (38,454 KB)