基于跨流注意力增强中心差分卷积网络的CG图像检测

黄锦坤; 黄远航; 黄文敏; 骆伟祺

doi:10.11959/j.issn.2096-109x.2024083

您当前的位置：

首页 >

文章列表页 >

基于跨流注意力增强中心差分卷积网络的CG图像检测

学术论文 | 更新时间：2025-02-06

- 基于跨流注意力增强中心差分卷积网络的CG图像检测
- Cross-stream attention enhanced central difference convolutional network for CG image detection
- 网络与信息安全学报 2024年10卷第6期页码：96-108
- 作者机构：
  
  1.中山大学计算机学院，广东广州 510006
  2.广东省信息安全技术重点实验室，广东广州 510006
- 作者简介：
  
  [ "黄锦坤（1999- ），男，广东揭阳人，中山大学硕士生，主要研究方向为图像伪造检测与定位。" ]
  [ "黄远航（1997- ），男，广东茂名人，中山大学博士生，主要研究方向为数字图像取证。" ]
  [ "黄文敏（1994- ），男，广东湛江人，中山大学博士生，主要研究方向为人脸属性编辑和图像伪造检测与定位。" ]
  [ "骆伟祺（1980- ），男，广东韶关人，博士，中山大学教授、博士生导师，主要研究方向为数字媒体伪造与检测、信息隐写与分析。" ]
- 基金信息：
  
  国家自然科学基金(62472458)
- DOI：10.11959/j.issn.2096-109x.2024083
  中图分类号： TP391
- 收稿：2024-04-05，
  
  修回：2024-08-11，
  
  纸质出版：2024-12-25
- 稿件说明：
移动端阅览
黄锦坤, 黄远航, 黄文敏, 等. 基于跨流注意力增强中心差分卷积网络的CG图像检测[J]. 网络与信息安全学报, 2024, 10(6): 96-108.

HUANG J K, HUANG Y H, HUANG W M, et al. Cross-stream attention enhanced central difference convolutional network for CG image detection[J]. Chinese Journal of Network and Information Security, 2024, 10(6): 96-108.
黄锦坤, 黄远航, 黄文敏, 等. 基于跨流注意力增强中心差分卷积网络的CG图像检测[J]. 网络与信息安全学报, 2024, 10(6): 96-108. DOI： 10.11959/j.issn.2096-109x.2024083.

HUANG J K, HUANG Y H, HUANG W M, et al. Cross-stream attention enhanced central difference convolutional network for CG image detection[J]. Chinese Journal of Network and Information Security, 2024, 10(6): 96-108. DOI： 10.11959/j.issn.2096-109x.2024083.

摘要

随着计算机图形学（computer graphics

CG）技术在图像生成领域的日益成熟，创造的图像逼真程度大幅提升。这些技术虽然在日常生活中被广泛应用并带来诸多便利，但同时也有着许多安全隐患，如果使用CG技术生成的伪造图像被恶意使用，在互联网、社交媒体上广泛传播，则可能对个人和企业权益造成损害。提出了一种创新的跨流注意力增强中心差分卷积网络，致力于提高CG图像检测的准确性。模型中构建了一个双流结构，旨在分别从图像中抽取语义特征和非语义的残差纹理特征。每个流中的普通卷积层被中心差分卷积所替代，这一改进使模型能同时提取图像中的像素强度信息和像素梯度信息。此外，通过引入一个跨流注意力增强模块，该模型在全局层面上增强了特征提取能力，并促进了两个特征流之间的互补。实验结果证明，基于跨流注意力增强中心差分卷积网络的CG图像检测方法相比现有方法具有更优的性能。此外，一系列消融实验进一步验证了所提模型设计的合理性。

Abstract

With the maturation of computer graphics (CG) technology in the field of image generation

the realism of created images has been improved significantly. Although these technologies are widely used in daily life and bring many conveniences

they also come with many security risks. If forged images generated using CG technology are maliciously used and widely spread on the Internet and social media

they may harm the rights of individuals and enterprises. Therefore

an innovative cross-stream attention enhanced central difference convolutional network was proposed

aiming at improving the accuracy of CG image detection. A dual-stream structure was constructed in the model

in order to extract semantic features and non-semantic residual texture features from the image. Vanilla convolutional layers in each stream were replaced by central difference convolutions

which allowed the model to simultaneously extract pixel intensity information and pixel gradient information from the image. Furthermore

by introducing a cross-stream attention enhancement module

the model enhanced feature extraction capability at the global level and promoted complementarity between the two feature streams. Experimental results demonstrate that this method outperforms existing methods. Additionally

a series of ablation experiments further verify the rationality of the proposed model design.

关键词

Keywords

references

NG T T , CHANG S F , HSU J , et al . Physics-motivated features for distinguishing photographic images and computer graphics [C ] // Proceedings of the 13th Annual ACM International Conference on Multimedia . New York : ACM , 2005 : 239 - 248 .

LYU S , FARID H . How realistic is photorealistic [J ] . IEEE Transactions on Signal Processing , 2005 , 53 ( 2 ): 845 - 850 .

WANG Y , MOULIN P . On discrimination between photorealistic and photographic images [C ] // Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings . Piscataway : IEEE Press , 2006 .

LI W X , ZHANG T , ZHENG E G , et al . Identifying photorealistic computer graphics using second-order difference statistics [C ] // Proceedings of the 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery . Piscataway : IEEE Press , 2010 : 2316 - 2319 .

WU R Y , LI X L , YANG B . Identifying computer generated graphics VIA histogram features [C ] // Proceedings of the 2011 18th IEEE International Conference on Image Processing . Piscataway : IEEE Press , 2011 : 1933 - 1936 .

FAN S , WANG R , ZHANG Y , et al . Classifying computer generated graphics and natural images based on image contour information [J ] . Journal of Information & Computational Science , 2012 , 9 ( 10 ): 2877 - 2895 .

QUAN W Z , WANG K , YAN D M , et al . Distinguishing between natural and computer-generated images using convolutional neural networks [J ] . IEEE Transactions on Information Forensics and Security , 2018 , 13 ( 11 ): 2772 - 2787 .

YAO Y , HU W T , ZHANG W , et al . Distinguishing computer-generated graphics from natural images based on sensor pattern noise and deep learning [J ] . Sensors , 2018 , 18 ( 4 ): 1296 .

HE P S , JIANG X H , SUN T F , et al . Computer graphics identification combining convolutional and recurrent neural networks [J ] . IEEE Signal Processing Letters , 2018 , 25 ( 9 ): 1369 - 1373 .

HE P S , LI H L , WANG H X , et al . Detection of computer graphics using attention-based dual-branch convolutional neural network from fused color components [J ] . Sensors , 2020 , 20 ( 17 ): 4743 .

ZHANG R S , QUAN W Z , FAN L B , et al . Distinguishing computer-generated images from natural images using channel and pixel correlation [J ] . Journal of Computer Science and Technology , 2020 , 35 ( 3 ): 592 - 602 .

QUAN W Z , WANG K , YAN D M , et al . Learn with diversity and from harder samples: Improving the generalization of CNN-based detection of computer-generated images [J ] . Forensic Science International: Digital Investigation , 2020 , 35 : 301023 .

YAO Y , ZHANG Z X , NI X , et al . CGNet: Detecting computer-generated images based on transfer learning with attention module [J ] . Signal Processing: Image Communication , 2022 , 105 : 116692 .

BAI W M , ZHANG Z P , LI B , et al . Robust texture-aware computer-generated image forensic: benchmark and algorithm [J ] . IEEE Transactions on Image Processing , 2021 , 30 : 8439 - 8453 .

FRIDRICH J , KODOVSKY J . Rich models for steganalysis of digital images [J ] . IEEE Transactions on Information Forensics and Security , 2012 , 7 ( 3 ): 868 - 882 .

YU Z T , ZHAO C X , WANG Z Z , et al . Searching central difference convolutional networks for face anti-spoofing [C ] // Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2020 : 5294 - 5304 .

CORTES C , VAPNIK V . Support-vector networks [J ] . Machine Learning , 1995 , 20 ( 3 ): 273 - 297 .

FISHER R A . The use of multiple measurements in taxonomic problems [J ] . Annals of Eugenics , 1936 , 7 ( 2 ): 179 - 188 .

魏康康 , 骆伟祺 , 刘明林 . 基于中心差分卷积和注意力的空域彩色图像隐写分析 [J ] . 软件学报 , 2024 , ( 12 ): 1 - 17 .

WEI K K , LUO W Q , LIU M L . Spatial color image steganalysis based on central difference convolution and attention [J ] . Journal of Software , 2024 , ( 12 ): 1 - 17 .

王金伟 , 张子荷 , 罗向阳 , 等 . 基于强化样本的伪孪生网络图像篡改定位模型 [J ] . 网络与信息安全学报 , 2024 , 10 ( 1 ): 33 - 47 .

WANG J W , ZHANG Z H , LUO X Y , et al . Pseudo-Siamese network image tampering localization model based on reinforced samples [J ] . Chinese Journal of Network and Information Security , 2024 , 10 ( 1 ): 33 - 47 .

DENG X Q , CHEN B L , LUO W Q , et al . Fast and effective global covariance pooling network for image steganalysis [C ] // Proceedings of the ACM Workshop on Information Hiding and Multimedia Security . New York : ACM , 2019 : 230 - 234 .

WEI K K , LUO W Q , TAN S Q , et al . Universal deep network for steganalysis of color image based on channel representation [J ] . IEEE Transactions on Information Forensics and Security , 2022 , 17 : 3022 - 3036 .

YE J , NI J Q , YI Y . Deep learning hierarchical representations for image steganalysis [J ] . IEEE Transactions on Information Forensics and Security , 2017 , 12 ( 11 ): 2545 - 2557 .

DOSOVITSKIY A , BEYER L , KOLESNIKOV A , et al . An image is worth 16×16 words: Transformers for image recognition at scale [EB ] . arXiv Preprint arXiv: 2010.11929 , 2020 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [J ] . Advances in Neural Information Processing Systems , 2017 , 30 .

TOKUDA E , PEDRINI H , ROCHA A . Computer generated images vs. digital photographs: a synergetic feature and classifier combination approach [J ] . Journal of Visual Communication and Image Representation , 2013 , 24 ( 8 ): 1276 - 1292 .

SELVARAJU R R , COGSWELL M , DAS A , et al . Grad-CAM: visual explanations from deep networks via gradient-based localization [J ] . International Journal of Computer Vision , 2020 , 128 ( 2 ): 336 - 359 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合色彩空间特征与频域特征的多源伪造图像检测方法

基于注意力机制与特征融合的网络钓鱼检测算法

基于程序过程间语义优化的深度学习漏洞检测方法

基于噪声注意力的伪造人脸检测方法

基于双分支网络的图像修复取证方法