隨著科技與網路的發展越來越高，圖像儼然已經成為了視覺信息的主要來源。而目前強大的圖形編輯軟體可以很輕易地改變原本的圖片內容，且不留下任何修改的痕跡，對圖像造成潛在的危險。在本論文中，我們提出一個基於深度神經網路偵測與定位圖像偽造的方法，其可以從人眼無法判別的偽造影像中學習並自動區分偽造和真實的圖像，此方法不僅可以偵測偽造的影像，更可以定位偽造圖像中被偽造的部分。由實驗結果可以清楚地看到，我們所提出的方法同時提供較好的成功偵測率和好的偽造影像定位。

With the development of technology and the Internet, images have become the main source of visual information. Current strong graphic editing software can easily change the original image without leaving any traces of modification, which causes a potential danger to the image. In this thesis, a method is proposed for detecting and locating image forgery based on deep neural network. It can learn to automatically detect forgery and real images from forged images. This method is not only for detecting forged images, but also for identifying forged parts in forged images. From the experimental results, the proposed method clearly provides better detection rates and good image forgery localization.

[1] Genevieve B. Orr. "The Perceptron". Willamette University. Retrieved 3 March 2017.
[2] ujjwalkarn. "An Intuitive Explanation of Convolutional Neural Networks". August 11, 2016
[3] Geoffrey E. Hinton. "Rectified Linear Units Improve Restricted Boltzmann Machines". University of Toronto
[4] Adit Deshpande. "A Beginner's Guide To Understanding Convolutional Neural Networks". UCLA
[5] G.E. Hinton and R.R. Salakhutdinov, "Reducing the Dimensionality of Data with Neural Networks", Science, 28 July 2006, Vol. 313. no. 5786, pp. 504 - 507.
[6] Smolensky, Paul (1986). "Chapter 6: Information Processing in Dynamical Systems: Foundations of Harmony Theory". In Rumelhart, David E.; McLelland, James L. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume 1: Foundations. MIT Press. pp. 194–281. ISBN 0-262-68053-X.
[7] Hinton, G. E. "A Practical Guide to Training Restricted Boltzmann Machines. " Department of Computer Science; University of Toronto. Aug. 2010
[8] E. Gopi, N. Lakshmanan, T. Gokul, S. KumaraGanesh, and P. R. Shah, "Digital image forgery detection using artificial neural network and auto regressive coefficients, " in Electrical and Computer Engineering, 2006. CCECE’06. Canadian Conference on. IEEE, 2006, pp. 194–197.
[9] J. Luka´s and J. Fridrich, "Estimation of primary quantization matrix in double compressed jpeg images, " in Proc. Digital Forensic Research, Workshop, 2003, pp. 5–8
[10] M.K. Johnson and H. Farid, "Exposing digital forgeries by detecting inconsistencies in lighting, " in ACM Multimedia and Security Workshop, 2005
[11] Wei Wang, Jing Dong and Tieniu Tan, "EFFECTIVE IMAGE SPLICING DETECTION BASED ON IMAGE CHROMA", National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, P.O. Box 2728, Beijing, P.R. China, 100190
[12] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. FeiFei, "ImageNet Large Scale Visual Recognition Challenge, " IJCV, vol. 115, no. 3, pp. 211–252, 2015.
[13] "CASIA Tampered Image Detection Evaluation Database," 2010, http://forensics.idealtest.org/casiav2/.
[14] "Core image dataset, " 2010, http://vision.cs.uiuc.edu/CORE/
[15] Srivastava, Nitish, et al. "Dropout: a simple way to prevent neural networks from overfitting", JMLR 2014
[16] "Dropout layer," https://leonardoaraujosantos.gitbooks.io/artificial-inteligence
[17] Ying Zhang, Jonathan Goh, Lei Lei Win and Vrizlynn Thing, "Image Region Forgery Detection: A Deep Learning Approach", Proceedings of the Singapore Cyber-Security Conference (SG-CRC) 2016
[18] Paolo Rota, Enver Sangineto, Valentina Conotter and Christopher Pramerdorfer, "Bad Teacher or Unruly Student: Can Deep Learning Say Something in Image Forensics Analysis? ", 2016 23rd International Conference on Pattern Recognition (ICPR) Cancún Center, Cancún, México, December 4-8, 2016
[19] Jason Bunk, Jawadul H. Bappy, Tajuddin Manhar Mohammed, Lakshmanan Nataraj, "Detection and Localization of Image Forgeries using Resampling Features and Deep Learning"
[20] Z. He, W. Lu, W. Sun, and J. Huang, "Digital image splicing detection based on Markov features in DCT and DWT domain, " Pattern Recognit., vol. 45, no. 12, pp. 4292–4299, Dec. 2012.
[21] G. Muhammad, M. Al–Hammadi, M. Hussain, G. Bebis, "Image forgery detection using steerable pyramid transform and local binary pattern, " Machine Vision and Applications, pp. 1–11, 2013.
[22] W. Wang, J. Dong, and T. Tan, "Effective image splicing detection based on image chroma, " in ICIP. IEEE, 2009, pp. 1257–1260.
[23] Bo X, Junwen W, Guangjie L, Yuewei D. " Image copy-move forgery detection based on SURF". In Multimedia information networking and security (MINES), 2010 international conference on;2010; Nanjing, China; 889–892.
[24] Kang L, Cheng X, Li K, Xiao C. "Copy-move forgery detection in digital image. " In IEEE 3rd international congress on image and signal processing; 2010; Yantai, China; 2419–2421.
[25] Davarzani R, Yaghmaie K, Mozaffari S, Tapak M. "Copy-move forgery detection using multiresolution local binary patterns. " Forensic Sci Int. 2013;231:61–72.
[26] Li L, Li S, Zhu H, Chu S, Roddick J, Pan J. "An efficient scheme for detecting copy-move forged images by local binary patterns. " J Inform Hid Multimedia Signal Process. 2013;4:46–56.
[27] Zimba M, Xingming S. "Fast and robust image cloning detection using block characteristics of DWT coefficients. " Int J Digital Cont Technol Appl. 2011;5:359–367.
[28] Zhao J, Guo J. "Passive forensics for copy-move image forgery using a method based on DCT and SVD. " Forensic Sci Int. 2013;233:158–166.
[29] Sunil K, Jagan D, Shaktidev M. "DCT-PCA based method for copy-move forgery detection. " In 48th annual convention of computer society of India on ICT and critical infrastructure; 2014; Vishakapatnam, India; 577–583.
[30] I. C. Chang, J. C. Yu, and C.-C. Chang. " A forgery detection algorithm for exemplar-based inpainting images using multi-region relation. " Image and Vision Computing, 31(1):57–71, January 2013.
[31] W. Wang, J. Dong, and T. Tan. "Exploring dct coefficient quantization effects for local tampering detection. " Information Forensics and Security, IEEE Transactions on, 9(10):1653–1666, Oct 2014.
[32] F. Zach, C. Riess, and E. Angelopoulou. "Automated image forgery detection through classification of jpeg ghosts. " Pattern Recognition, 7476:185–194, January 2012.
[33] I. Amerini, L. Ballan, R. Caldelli, A. D. Bimbo, and G. Serra. "A sift-based forensic method for copy and move attack detection and transformation recovery. " IEEE Transactions on Information Forensics and Security, 6(3):1099–1110, March 2011.
[34] V. Christlein, C. Riess, J. Jordan, C. Riess, and E. Angelopoulou. "An evaluation of popular copy-move forgery detection approaches. " IEEE Transactions on Information Forensics and Security, 7(6):1841– 1854, December 2012.
[35] P. Kakar and N. Sudha. "Exposing postprocessed copy-paste forgeries through transform-invariant feature. " IEEE Transactions on Information Forensics and Security, 7(3):1018–1028, June 2012.
[36] Lin H, Wang C, Kao Y. "Fast copy-move forgery detection. " WSEAS Trans Signal Process. 2009;5:188–197.
[37] Bayram S, Sencar H, Memon N. "An efficient and robust method for detecting copy-move forgery. " In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2009; Taipei, Taiwan; 1053–1056.
[38] Hsu Yu-Feng, Chang S. "Camera response functions for image forensics: An automatic algorithm for splicing detection. " IEEE Trans Inform Forensics Secur. 2010;5:816–825.
[39] Fang Z, Wang S, Zhang X. "Image splicing detection using camera characteristic inconsistency. " In International Conference on Multimedia Information Networking and Security (MINES’09); 2009; Hubei, China; 20-24.
[40] Hashmi MF, Anand V, Keskar AG. "Copy-move image forgery detection using an efficient and robust method combining un-decimated wavelet transform and scale invariant feature transform. " AASRI Procedia. 2014;9:84–91.