网络与信息安全学报2024，Vol.10Issue(2)：182-189,8.DOI:10.11959/j.issn.2096-109x.2024016
基于孪生网络的鲁棒性深度伪造检测方法
Robust deepfake detection method based on siamese network
摘要
Abstract
The proliferation of deepfake(DF)technology for generating manipulated facial expressions in synthetic images has raised concerns due to its potential negative impacts on individuals and society.In response to the need for robust detection,researchers have been developing methods to identify deepfakes.While current detection methods perform well on high-quality images,they often falter when confronted with low-quality or compressed images.This study focused on enhancing the robustness of deepfake detection methods to address these limitations.A novel approach leveraging a Siamese network was proposed,designed to learn common forgery features across both high-quality and low-quality images.This was achieved by trading off some of the high-quality image feature extraction capabilities to bolster the representational capacity for low-quality images.The proposed method demonstrated an average accuracy exceeding 90%across various datasets with different compression levels,surpassing several existing detection techniques.The simplicity,effectiveness,and adaptability of the proposed method to different backbone networks were further substantiated through ablation experiments.关键词
伪造取证/深度伪造检测/孪生网络/鲁棒性Key words
forgery forensics/deepfake detection/siamese network/robustness分类
信息技术与安全科学引用本文复制引用
林善和..基于孪生网络的鲁棒性深度伪造检测方法[J].网络与信息安全学报,2024,10(2):182-189,8.基金项目
福建省创新战略研究计划项目(No.2023R0156)The Innovation Strategic Research Plan Project of Fujian Province(No.2023R0156) （No.2023R0156）
