Improved Detection of Forged and Generated Facial Images Based on ResNet-50

Yanbei Zhang*, Bintao Hu, Wenzhang Zhang, Md Maruf Hasan, Hengyan Liu

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Detecting forged and generated images has recently grown into an emerging research area. As forgery and generation technologies advance, they pose risks of personal privacy and public security. Existing algorithms are designed to detect either forged or generated facial images. Due to a lack of generalizability, their performance usually degrades when faced with a mixture of both types. To tackle this problem, this paper proposes a framework Res50_Attn_DSCE that enhances generalizability and extracts both local and global features, thereby improving the algorithm's performance across different types of datasets. Additionally, depth-separable convolution reduces computational costs. Experimental results demonstrate that our proposed model achieves the highest accuracy with the shortest runtime. Compared to other traditional algorithms, these results validate the effectiveness of our model's improvements.

Original languageEnglish
Title of host publicationProceedings - 2024 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discover, CyberC 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages199-205
Number of pages7
ISBN (Electronic)9798331506896
DOIs
Publication statusPublished - 2024
Event16th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discover, CyberC 2024 - Guangzhou, China
Duration: 24 Oct 202426 Oct 2024

Publication series

NameProceedings - 2024 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discover, CyberC 2024

Conference

Conference16th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discover, CyberC 2024
Country/TerritoryChina
CityGuangzhou
Period24/10/2426/10/24

Keywords

  • Depth-Separable Convolution
  • Forged Image Detection
  • Generated Image Detection
  • Self-Attention

Fingerprint

Dive into the research topics of 'Improved Detection of Forged and Generated Facial Images Based on ResNet-50'. Together they form a unique fingerprint.

Cite this