TY - GEN
T1 - Improved Detection of Forged and Generated Facial Images Based on ResNet-50
AU - Zhang, Yanbei
AU - Hu, Bintao
AU - Zhang, Wenzhang
AU - Hasan, Md Maruf
AU - Liu, Hengyan
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Depth-Separable Convolution
KW - Forged Image Detection
KW - Generated Image Detection
KW - Self-Attention
UR - http://www.scopus.com/inward/record.url?scp=85215106825&partnerID=8YFLogxK
U2 - 10.1109/CyberC62439.2024.00042
DO - 10.1109/CyberC62439.2024.00042
M3 - Conference Proceeding
AN - SCOPUS:85215106825
T3 - Proceedings - 2024 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discover, CyberC 2024
SP - 199
EP - 205
BT - Proceedings - 2024 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discover, CyberC 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discover, CyberC 2024
Y2 - 24 October 2024 through 26 October 2024
ER -