EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DDS: Deepfake Detection System through Collective Intelligence and Deep-Learning Model in Blockchain Environment

Nakhoon Choi, Heeyoul Kim

Applied Sciences · 07.02.2023 · 13 (4) · 2122

DOI: 10.3390/app13042122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 07.02.2023. Verfasst von Nakhoon Choi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kyonggi University Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the spread of mobile devices and the improvement of the mobile service environment, the use of various Internet content providers (ICPs), including content services such as YouTube and video hosting services, has increased significantly. Video content shared in ICP is used for information delivery and issue checking based on accessibility. However, if the content registered and shared in ICP is manipulated through deepfakes and maliciously distributed to cause political attacks or social problems, it can cause a very large negative effect. This study aims to propose a deepfake detection system that detects manipulated video content distributed in video hosting services while ensuring the transparency and objectivity of the detection subject. The detection method of the proposed system is configured through a blockchain and is not dependent on a single ICP, establishing a cooperative system among multiple ICPs and achieving consensus for the common purpose of deepfake detection. In the proposed system, the deep-learning model for detecting deepfakes is independently driven by each ICP, and the results are ensembled through integrated voting. Furthermore, this study proposes a method to supplement the objectivity of integrated voting and the neutrality of the deep-learning model by ensembling collective intelligence-based voting through the participation of ICP users in the integrated voting process and ensuring high accuracy at the same time. Through the proposed system, the accuracy of the deep-learning model is supplemented by utilizing collective intelligence in the blockchain environment, and the creation of a consortium contract environment for common goals between companies with conflicting interests is illuminated.

Förderung

  • Kyonggi University Research

Zitieren

APA

Choi, N., & Kim, H. (2023). DDS: Deepfake Detection System through Collective Intelligence and Deep-Learning Model in Blockchain Environment. Applied Sciences, 13(4), 2122. https://doi.org/10.3390/app13042122

Vancouver

Choi N, Kim H. DDS: Deepfake Detection System through Collective Intelligence and Deep-Learning Model in Blockchain Environment. Applied Sciences. 2023;13(4):2122. doi:10.3390/app13042122

BibTeX
@article{Choi2023,
  author = {Choi, Nakhoon and Kim, Heeyoul},
  title = {DDS: Deepfake Detection System through Collective Intelligence and Deep-Learning Model in Blockchain Environment},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {4},
  pages = {2122},
  doi = {10.3390/app13042122}
}
Kostenlos starten →