摘要
目前,使用深度伪造技术合成伪造人脸图像的案例非常广泛,深度伪造技术通过对人脸图像进行面部替换或表情更改,从而实现深度伪造的目的。这类深度伪造图像的肆意传播,可能对社会和个人造成许多不良后果。因此,不少学者着手研究深度伪造检测方法。虽然现有的检测方法在高质量图像的检测上能实现非常高的准确率,但是在检测经过图像压缩操作的低质量人脸图像时,其检测精度会大幅下降。研究旨在改进现有深度伪造检测方法鲁棒性不足的问题。为此,提出了一种基于孪生网络的深度伪造检测方法,其思想是使用孪生网络来学习高质量图像和低质量图像之间公共伪造特征,通过牺牲部分高质量图像的特征提取能力,来提高网络对低质量图像的表征能力,从而使网络在不同压缩率伪造图像的检测上都具有较高的准确率。实验结果表明,所提方法在多个不同压缩率数据集上的综合平均准确率达到90%以上,优于多个现有检测方法。通过消融实验证明所提方法简单有效,且适用于不同的主干网络。
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.
作者
林善和
LIN Shanhe(Fujian Star-net Communication Company Limited,Fuzhou 350117,China)
出处
《网络与信息安全学报》
2024年第2期182-189,共8页
Chinese Journal of Network and Information Security
基金
福建省创新战略研究计划项目(No.2023R0156)。
关键词
伪造取证
深度伪造检测
孪生网络
鲁棒性
forgery forensics
deepfake detection
siamese network
robustness
