融入混合注意力的低缩放因子Seam Carving篡改检测算法

赵洁; 常皓婵; 武斌

doi:10.11959/j.issn.2096-6652.202414

您当前的位置：

首页 >

文章列表页 >

融入混合注意力的低缩放因子Seam Carving篡改检测算法

学术论文 | 更新时间：2024-08-06

- 融入混合注意力的低缩放因子Seam Carving篡改检测算法
- Low scaling factor Seam Carving tamper detection algorithm with hybrid attention
- 智能科学与技术学报 2024年6卷第2期页码：244-252
- 作者机构：
  
  天津城建大学计算机与信息工程学院，天津 300384
- 作者简介：
  
  [ "赵洁（1984- ），男，博士，天津城建大学计算机与信息工程学院副教授，主要研究方向为图像处理、计算机视觉、机器学习。" ]
  [ "常皓婵（2000- ），女，天津城建大学计算机与信息工程学院硕士生，主要研究方向为图像取证、机器学习。" ]
  [ "武斌（1966- ），男，天津城建大学计算机与信息工程学院教授，主要研究方向为计算机视觉、模式识别。" ]
- 基金信息：
  
  天津市重点研发计划科技支撑重点项目(19YFZCGX00130);天津市企业科技特派员项目(19JCTPJC47200)
- DOI：10.11959/j.issn.2096-6652.202414
  中图分类号： TP309.2
- 收稿：2024-03-15，
  
  修回：2024-05-22，
  
  纸质出版：2024-06-15
- 稿件说明：
移动端阅览
赵洁,常皓婵,武斌.融入混合注意力的低缩放因子Seam Carving篡改检测算法[J].智能科学与技术学报,2024,06(02):244-252.

ZHAO Jie,CHANG Haochan,WU Bin.Low scaling factor Seam Carving tamper detection algorithm with hybrid attention[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):244-252.
赵洁,常皓婵,武斌.融入混合注意力的低缩放因子Seam Carving篡改检测算法[J].智能科学与技术学报,2024,06(02):244-252. DOI： 10.11959/j.issn.2096-6652.202414.

ZHAO Jie,CHANG Haochan,WU Bin.Low scaling factor Seam Carving tamper detection algorithm with hybrid attention[J].Chinese Journal of Intelligent Science and Technology,2024,06(02):244-252. DOI： 10.11959/j.issn.2096-6652.202414.

摘要

针对现有的Seam Carving篡改检测算法对于低缩放因子情况存在检测精度不高、鲁棒性不强的问题，提出一种融入混合注意力机制的Seam Carving篡改检测算法。首先，利用BayarConv2D约束卷积对图像进行预处理，充分学习图像的噪声特征，并通过矩阵乘法与RGB图像进行特征融合；然后，采用ResNet作为骨干网络进行特征学习，引入残差传播和残差反馈机制，凸显Seam Carving的操作痕迹；最后，利用混合注意力机制同时提取相邻位置和通道之间的特征，更好地捕捉全局特征，进而将其输入全连接层进行分类。实验结果表明，在BOSSbase1.01数据集上，当缩放因子为1%和9%时，检测精度分别达到了89.48%和97.94%，优于现有主流方法，同时具有较低的计算复杂度和较好的鲁棒性，能够抵抗JPEG压缩攻击。

Abstract

The existing seam carving tamper detection algorithms have the problems of low detection accuracy and weak robustness for the case of low scaling factor. A seam carving tamper detection algorithm integrated with hybrid attention mechanism is proposed. Firstly

BayarConv2D constrained convolution is used to preprocess the image

fully learn the noise characteristics of the image

and fuse the features with RGB image through matrix multiplication. Then

ResNet is used as the backbone network for feature learning

and the residual propagation and residual feedback mechanisms are introduced to highlight the operation traces of seam carving. Finally

the hybrid attention mechanism is used to simultaneously extract the features between adjacent locations and channels to better capture the global features

and then input them into the full connection layer to achieve classification. The experimental results show that on the BOSSBase1.01 dataset

when the scaling factor is 1% and 9%

the detection accuracy of the proposed method reaches 89.48% and 97.94% respectively

which is better than existing mainstream methods. At the same time

it has lower computational complexity and better robustness

and can resist JPEG compression attacks.

关键词

Keywords

references

吴晶辉, 严彩萍, 李红, 等. 边缘引导的双注意力图像拼接检测网络[J]. 中国图象图形学报, 2024, 29(2): 430-443.

WU J H, YAN C P, LI H, et al. BDA-Net: boundary-guided dual attention network for image splicing detection[J]. Journal of Image and Graphics, 2024, 29(2): 430-443.

VIJAYALAKSHMI K N V S K, SASIKALA J, SHANMUGANATHAN C. Copy-paste forgery detection using deep learning with error level analysis[J]. Multimedia Tools and Applications, 2024, 83(2): 3425-3449.

李莉, 曾伟良, 黄永慧, 等. 基于半监督学习的人脸识别反欺骗方法研究[J]. 智能科学与技术学报, 2021, 3(3): 370-380.

LI L, ZENG W L, HUANG Y H, et al. Research on anti-spoofing method of face recognition based on semi-supervised learning[J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(3): 370-380.

GHOSH A, REDDY N D, MERTZ C, et al. Learned two-plane perspective prior based image resampling for efficient object detection[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2023: 13364-13373.

赵俊杰, 王金伟, 吴俊凤. 基于多质量因子压缩误差的对抗样本攻击方法识别[J]. 中国图象图形学报, 2023, 28(3): 850-863.

ZHAO J J, WANG J W, WU J F. Adversarial attack method identification model based on multi-factor compression error[J]. Journal of Image and Graphics, 2023, 28(3): 850-863.

AGARWAL S, JUNG K H. Median filtering detection using optimal multi-direction threshold on higher-order difference pixels[J]. Multimedia Tools and Applications, 2023, 82(20): 30875-30893.

PENG Y F, LIU X X, WANG G, et al. Irregular shape image retargeting based on seam carving[C]//Proceedings of the 2023 IEEE 3rd International Conference on Electronic Technology, Communication and Information (ICETCI). Piscataway: IEEE Press, 2023: 1845-1848.

LI L, XUE J R, TIAN Z Q, et al. Moment feature based forensic detection of resampled digital images[C]//Proceedings of the 21st ACM International Conference on Multimedia. New York: ACM, 2013: 569-572.

SHAMIR A, AVIDAN S. Seam carving for media retargeting[J]. Communications of the ACM, 2009, 52(1): 77-85.

SARKAR A, NATARAJ L, MANJUNATH B S. Detection of seam carving and localization of seam insertions in digital images[C]//Proceedings of the 11th ACM Workshop on Multimedia and Security. New York: ACM, 2009: 107-116.

WATTANACHOTE K, SHIH T K, CHANG W L, et al. Tamper detection of JPEG image due to seam modifications[J]. IEEE Transactions on Information Forensics and Security, 2015, 10(12): 2477-2491.

YIN T, YANG G B, LI L D, et al. Detecting seam carving based image resizing using local binary patterns[J]. Computers & Security, 2015, 55: 130-141.

KARAPINAR SENTURK Z, AKGUN D. A machine learning method for detecting the trace of seam carving[J]. Elektronika Ir Elektrotechnika, 2021, 27(5): 59-66.

FERNANDODA SILVA CIESLAK L, AUGUSTOPONTARA DA COSTA K, PAULOPAPA J. Seam carving detection using convolutional neural networks[C]//Proceedings of the 2018 IEEE 12th International Symposium on Applied Computational Intelligence and Informatics (SACI). Piscataway: IEEE Press, 2018: 195-200.

YE J Y, SHI Y X, XU G S, et al. A convolutional neural network based seam carving detection scheme for uncompressed digital images[C]//Proceedings of International Workshop on Digital Watermarking. Cham: Springer, 2019: 3-13.

BOROUMAND M, CHEN M, FRIDRICH J. Deep residual network for steganalysis of digital images[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(5): 1181-1193.

NAM S H, AHN W, YU I J, et al. Deep convolutional neural network for identifying seam-carving forgery[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(8): 3308-3326.

NATARAJ L, GUDAVALLI C, MANHAR MOHAMMED T, et al. Seam carving detection and localization using two-stage deep neural networks[C]//Proceedings of Machine Learning, Deep Learning and Computational Intelligence for Wireless Communication. Singapore: Springer, 2021: 381-394.

MOREIRA T P, SANTANA M C S, PASSOS L A, et al. An end-to-end approach for seam carving detection using deep neural networks[C]//Proceedings of Iberian Conference on Pattern Recognition and Image Analysis. Cham: Springer, 2022: 447-457.

XIA M, CHEN J Y, YANG G B, et al. Robust detection of seam carving with low ratio via pixel adjacency subtraction and CNN-based transfer learning[J]. Journal of Information Security and Applications, 2023, 75: 103522.

BAYAR B, STAMM M C. Constrained convolutional neural networks: a new approach towards general purpose image manipulation detection[J]. IEEE Transactions on Information Forensics and Security, 2018, 13(11): 2691-2706.

ZHANG R Y, NI J Q. A dense U-net with cross-layer intersection for detection and localization of image forgery[C]//Proceedings of the ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway: IEEE Press, 2020: 2982-2986.

HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2016: 770-778.

ZHANG D Y, ZHU W J, DING X L, et al. SRTNet: a spatial and residual based two-stream neural network for deepfakes detection[J]. Multimedia Tools and Applications, 2023, 82(10): 14859-14877.

CELEBI N H, HSU T L, LIU Q Z. A comparison study to detect seam carving forgery in JPEG images with deep learning models[J]. Journal of Surveillance, Security and Safety, 2022, 3(3): 88-100.

GUDAVALLI C, ROSTEN E, NATARAJ L, et al. SeeTheSeams: localized detection of seam carving based image forgery in satellite imagery[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE Press, 2022: 1-11.

WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of European Conference on Computer Vision. Cham: Springer, 2018: 3-19.

BAS P, FILLER T, PEVNÝ T. "Break our steganographic system": the ins and outs of organizing BOSS[C]//Proceedings of International Workshop on Information Hiding. Heidelberg: Springer, 2011: 59-70.

SCHAEFER G, STICH M. UCID: an uncompressed color image database[C]//Proceedings of Storage and Retrieval Methods and Applications for Multimedia 2004. [S.l.:s.n.], 2003: 472-480.

浏览量

316

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Cerberus：基于深度学习的跨站社交网络机器人检测系统