哈尔滨商业大学学报（自然科学版）2026，Vol.42Issue(1)：34-41,8.
基于全局频谱感知网络的深度伪造检测
A method based on global spectral awareness network for deepfake detection
摘要
Abstract
The rapid development of Generative Adversarial Networks(GANs)led to each generative model introducing unique artifacts.Current forgery detection models performed poorly when faced with images generated by multiple models.To address this,a Global Spectral Awareness Network(GSANet)was proposed.A Multi-Scale Spectral Learning module(MSSL)was designed,which directly performed multi-scale learning on the spectrum to enhance the ability to extract frequency domain features.High-Frequency Information Extraction module(HFIE)was employed,which forced the model to consistently focus on high-frequency information.The tendency of overfitting was effectively mitigated through emphasizing the importance of high-frequency information.Dilated Squeeze Attention module(DSA)was constructed.Dilated convolution was combined with attention mechanisms to replace the 3×3 convolution in the ResNet bottleneck block,and a DSA Block was formed for global feature learning.This enabled the model to achieve more generalized deepfake detection.Validation on eight different GAN-generated test sets demonstrated a significant 4％performance improvement.关键词
伪造检测/频谱学习/高频信息/特征提取/空洞挤压Key words
deepfake detection/spectral learning/high-frequency information/extracting features/dilated squeeze-attention分类
信息技术与安全科学引用本文复制引用
李子龙,杨高明..基于全局频谱感知网络的深度伪造检测[J].哈尔滨商业大学学报（自然科学版）,2026,42(1):34-41,8.基金项目
安徽理工大学2023年度医学专项培育项目(YZ2023H2B00) （YZ2023H2B00）
