Video Forensics in Temporal Domain using Machine Learning Techniques

Full Text (PDF, 477KB), PP.58-67

Views: 0 Downloads: 0

Author(s)

Sunil Jaiswal 1,* Sunita Dhavale 1

1. Defence Institute of Advanced Technology, Pune- 411025, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijcnis.2013.09.08

Received: 21 Dec. 2012 / Revised: 27 Mar. 2013 / Accepted: 11 May 2013 / Published: 8 Jul. 2013

Index Terms

Digital forensics, Temporal forensics, Discrete Cosine Transform, Discrete Fourier Transform, Discrete Wavelet Transform, Support Vector Machine, Ensemble based classifier

Abstract

In defence and military scenarios, Unmanned Aerial Vehicle (UAV) is used for surveillance missions. UAV's transmit live video to the base station. Temporal attacks may be carried out by the intruder during video transmission. These temporal attacks can be used to add/delete objects, individuals, etc. in the live transmission feed. This can cause the video information to misrepresent facts of the UAV transmission. Hence, it is needed to identify the fake video from the real ones. Compression techniques like MPEG, H.263, etc. are popularly used to compress videos. Attacker can either add/delete frames from videos to introduce/remove objects, individuals etc. from video. In order to perform attack on the video, the attacker has to uncompress the video and perform addition/deletion of frames. Once the attack is done, the attacker needs to recompress the frames to a video. Wang and Farid et. al. [1] proposed a method based on double compression technique to detect temporal fingerprints left in the video caused due to frame addition/deletion. Based on double MPEG compression, here we propose a video forensic technique using machine learning techniques to detect video forgery. In order to generate a unique feature vector to identify forged video, we analysed the effect of attacks on Prediction Error Sequence (PES) in various domains like Discrete Cosine Transform (DCT), Discrete Fourier Transform (DFT), Discrete Wavelet Transform (DWT) domain etc. A new PES feature γ is defined and extracted from DWT domain, which is proven robust training parameter for both Support Vector Machine (SVM) and ensemble based classifier. The trained SVM was tested for unknown videos to find video forgery. Experimental results show that our proposed video forensic is robust and efficient in detecting video forgery without any human intervention. Further the proposed system is simpler in design and implementation and also scalable for testing large number of videos.

Cite This Paper

Sunil Jaiswal, Sunita Dhavale, "Video Forensics in Temporal Domain using Machine Learning Techniques", International Journal of Computer Network and Information Security(IJCNIS), vol.5, no.9, pp.58-67, 2013. DOI:10.5815/ijcnis.2013.09.08

Reference

[1]Weihong Wang, Hany Farid, "Exposing Digital foregeries in Video by Detecting Double MPEG Compression," in Proc. ACM Multimedia and Security Workshop, Geneva, Switzerland, 2006, pp. 37–47.
[2]Matthew C. Stamm, W. Sabrina Lin and K. J. Ray Liu, "Temporal Forensics and Anti-Forensics for Motion Compensated Video," in IEEE Transactions On Information Forensics and Security, Vol. 7, No. 4, August 2012, pp. 1315-1329.
[3]Asma Rabaoui, Manuel Davy, Stéphane Rossignol, and Noureddine Ellouze , "Using One-Class SVMs and Wavelets for Audio Surveillance" in IEEE Transactions On Information Forensics and Security, VOL. 3, NO. 4, December 2008,pp. 763-775..
[4]Cheng-Liang Lai,Yi-Shiang Chen "The Application of Intelligent System to Digital Image Forensics", Proceedings of the Eighth International Conference on Machine Learning and Cybernetics, Baoding, 12-15 July 2009, pp. 2991-2998.
[5]The MPEG Handbook, 1st ed., Elsevier Group, John Watkinson,2001, pp. 140-208.
[6]A beginners guide for MPEG-2 standard.Available: http://www.fh-friedberg.de/fachbereiche/e2/telekom-labor/zinke/mk/mpeg2beg/beginnzi.htm
[7]Basic Video Coding and MPEG. Available: http://www-ee.uta.edu/dip/courses/ee5356/631pub04_sec12videoMPEG.ppt
[8]"Pattern Recognition in Matlab", K.Koutroumbas ,Elsevier,2009.
[9]Digital Image Processing, 3rd ed., Pearson Education, Rafael C. Gonzalez,Richard E. Woods,2009, pp. 510-512.
[10]MPEG-2 overview and MATLAB codec project. Available: http://www.cs.cf.ac.uk/Dave/Multimedia/Lecture_Examples/Compression/mpegproj/
[11]Xiph.org Video Test Media.Available : http://media.xiph.org/video/derf/.
[12]"Image processing and Pattern Recognition", Frank Y. Shih, Wiley, 2010.
[13]Jan Kodovský, Jessica Fridrich and VojtÄ›ch Holub, "Ensemble Classifiers for Steganalysis of Digital Media", IEEE Transactions on Information Forensics and Security, Vol. 7, No. 2, April 2012, pp. 432-444.
[14]Gabriele Zenobi, Pádraig Cunningham " Using Diversity in Preparing Ensembles of Classifiers Based on Different Feature Subsets to Minimize Generalization Error", Department of Computer Science, Trinity College Dublin, pp 1-15.
[15]Lior Rokach, "Ensemble Methods for classifiers" Chapter 45, Department of Industrial Engineering, Tel-Aviv University, pp. 957-962.
[16]Lena Kallin Westin, "Receiver operating characteristic (ROC) analysis" ,Department of Computing Science, Umeå University, Available: www8.cs.umu.se/research/reports/2001/018/part1.pdf
[17]"Introduction to ROC Curves" , Available : http://gim.unmc.edu/dxtests/ROC1.htm