融合手工特征与深度学习，提升深伪图像检测能力
Enhanced Deep Learning DeepFake Detection Integrating Handcrafted Features
- 将频域手工特征与RGB图像输入结合，增强判别力
- 在DeepFake Detection Challenge数据集上准确率达97.6%
- 适合需要高精度身份验证的安防场景
深度伪造和人脸替换技术的快速发展引发了数字安全领域的重大担忧，尤其是在身份验证和注册流程中。传统检测方法往往难以泛化应对复杂的面部篡改。本研究提出一种增强型深度学习检测框架，将手工提取的频域特征与常规的RGB输入相结合。该混合方法利用图像篡改过程中引入的频率域与空间域伪影，为分类器提供更丰富、更具区分性的信息。评估了多种频域手工特征，包括隐写分析富模型（Steganalysis Rich Model）、离散余弦变换（DCT）、误差等级分析（ELA）、奇异值分解（SVD）和离散傅里叶变换（DFT）。
原文摘要 · Abstract (English)
The rapid advancement of deepfake and face swap technologies has raised significant concerns in digital security, particularly in identity verification and onboarding processes. Conventional detection methods often struggle to generalize against sophisticated facial manipulations. This study proposes an enhanced deep-learning detection framework that combines handcrafted frequency-domain features with conventional RGB inputs. This hybrid approach exploits frequency and spatial domain artifacts introduced during image manipulation, providing richer and more discriminative information to the classifier. Several frequency handcrafted features were evaluated, including the Steganalysis Rich Model, Discrete Cosine Transform, Error Level Analysis, Singular Value Decomposition, and Discrete Fourier Transform
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。