articleACM Computing SurveysMar 16, 2026HYBRID OA

Deepfake Generation and Detection: A Benchmark and Survey

GPGan PeiJZJiangning ZhangMHMenghan HuZZZhenyu ZhangCWChengjie Wang

East China Normal University · Zhejiang University · +4 more institutions

Indexed incrossref

Abstract

Deepfake technology aims to synthesize highly realistic facial images and videos, with broad application potential in entertainment, film production, and digital human modeling. Deep learning has driven major progress in generative modeling, from VAEs and GANs to the recent rise of diffusion models. The latter have sparked a renewed wave of research through their superior generation quality. In addition to deepfake generation, corresponding detection technologies continuously evolve to regulate the potential misuse of deepfakes, such as privacy invasion and phishing attacks. This survey comprehensively reviews the latest developments in deepfake generation and detection, summarizing and analyzing current…

Citation impact

5
total citations
FWCI
91.41
Percentile
99%
References
146
Citations per year

Authors

9
  • GP
    Gan PeiCorresponding

    East China Normal University

  • JZ
    Jiangning Zhang

    Zhejiang University

  • MH
    Menghan Hu

    East China Normal University

  • ZZ
    Zhenyu Zhang

    Nanjing University

  • CW
    Chengjie Wang

    Tencent (China)

Topics & keywords

Topics
Keywords
  • Benchmark (surveying)
  • Face (sociological concept)
  • Key (lock)
  • Task (project management)
  • Generative grammar
UN Sustainable Development Goals
  • Peace, Justice and strong institutions
No related works found for this paper.

Funding