Satellite Conference ICSTSD 2016 International Conference on Science and Technology for Sustainable Development, Kuala Lumpur, MALAYSIA, May 24-26, 2016

IMPLEMENTATION OF VIDEO FORENSICS FRAME WORK FOR VIDEO SOURCE IDENTIFICATION Monika R Chourasiya

Prof. Avinash P Wadhe

Student of Master of Engineering (Computer Science & Engineering) Raisoni College of Engineering and Management Amravati, India . Abstract— Forensic science is the application of science to criminal and civil laws. Forensic scientists collect, preserve, and analyze scientific evidence during the course of an investigation. Digital forensics deals with the process of uncovering and interpreting electronic data. The goal of the process is to preserve any evidence in its most original form while performing a structured investigation by collecting, identifying and validating the digital information for the purpose of reconstructing past events. Digital forensic science (DFS) is the controlled extraction and analysis of legally admissible evidence from digital storage device. Wireless communication is the fastest growing segment of the communications industry. Many of the videos now a day are transferred through the wireless medium which can be sometime used as a proof of evidence. Modern era is rapidly shifting from analog to digital world. The advance digital technologies have brought us numerous cheap yet good-quality imaging devices to capture into the digital videos, so it became a big challenge to identify the source of video which are used as a proof of evidence in forensic field. Video source identification is employed to track down piracy crimes. Keywords—Digital Forensics, Video Forensics,Video Source Identification,

I.

INTRODUCTION

Forensic Science is a scientific field that is applied to the field of law. Forensic investigation endeavors to use science to uncover the transferred evidence and discern its meaning. With the increasing accessibility of technology for everyday people, things are starting to get digitalized: digital camera, digital cable, digital sound digital video. This development has led to the rise. of digital forensics, the uncovering and examination of evidence located on all things electronic with digital storage, including computers, cell phones, and networks. Digital forensics researchers and practitioners stand at the forefront of some of the most challenging problems in

ISSN: 2348 – 8387

Head of Department, Computer Science & Engineering Raisoni College of Engineering and Management Amravati, India.

computer science, including “big data” analysis, natural language processing, data visualizations, and cyber security. Digital forensics is the use of analytical and investigative techniques to identify, collect, examine and preserve evidence or the information which is magnetically stored or encoded, usually to provide digital evidence of a specific or general activity[7]. Since, the voluntary or natural content manipulations, such as analog to digital conversions (camcorder capture), compression, frame removing or adding (advertising), a multimedia identification/authentication has increased rapidly the process has to withstand with these natural distortions. Digital videos and photographs can be no longer considered “proof of evidence/occurrence” since their origin and integrity cannot be trusted [17]. Whenever there comes a cybercrime case related to multimedia, the very first question which arises in a mind is what the source of this suspect multimedia is. As the digital videos and the images can be used as the proof of evidence it becomes very necessary to identify the source of the video, else it can be forged or derived from an untrustworthy source, which makes the evidence invalid. Source identification plays a very vital role in the field of digital forensics. Source identification (or sensor forensics) aims at identifying the acquisition device that captured an image (digital camera, cellphone or scanner).[24]. II LITERATURE SURVEY Monika Chourasiya and Avinash Wadhe,[24], In this paper the authors had reviewed the various methods used for the identification of the multimedia sources. Now a days as most of the videos are transmitted through the wireless media which can sometimes be used as a proof of evidence but due to the advanced technologies which are used for manipulating the videos and images it has became very essential to authenticate

www.internationaljournalssrg.org

Page 129

Satellite Conference ICSTSD 2016 International Conference on Science and Technology for Sustainable Development, Kuala Lumpur, MALAYSIA, May 24-26, 2016

the videos or the images. Authenticity is provided so that if any of these videos or images is considered as the proof of evidence it must be considered as valid proof. So, in this paper the author has used the IP address, system information, video information, MAC address to identify the source of the video.

verify its authentication through IP address, information, Video Information and MAC address.

Naveen Sharma, Anwer Reyaz J, Balan C[23], In this paper the author had used the wavelet based technique to identify the source. Peak-to-Correlation Energy (PCE) criteria is used to check the correlation performance. The advantage of the method described here is that it works for almost all type of digital camera as well as mobiles phone cameras with high accuracy.

Step 1: Select carrier image I. Step 2: Input IP address, system information, video information, MAC address Step 3: Convert IP address, system information, video information, MAC address into Binary form. Step 4: Sample binary into N samples. Step 5: Generate Key L(Ki)=L(Ns) Step 6: (for i=0 to L(Ki) Read Ip(i) Extract Ip(i)= R,G,B Split R=(2(msb)+6(lsb)) bits G=(2(msb)+6(lsb)) bits B==(2(msb)+6(lsb)) bits Replace R(lsb)=Nsi G(lsb)=Nsi+1 B(lsb)=Nsi+2 i=i+3 Convert R,G,B into pixels Pi Set Pi to Image I End Step 7: Stop

Alex C. Kot and Hong Cao[15], The authors in this paper had introduced the forensic role of source identification in multimedia forensics and reviewed the major developments in different types of source identification tasks. Methods for identification of software tools, e.g. source RAW converters and multimedia encoders, are also developed through detection of demosaicing regularity and intrinsic compression characteristics. The works based on detecting PRNU sensor noise pattern achieves excellent results. Yanmei Fang , Ahmet Emir Dirik , Xiaoxi Sun , Nasir Memon[10],In this paper the author had focused on building a classifier to effectively distinguish between digital images taken from digital single lens reflex (DSLR) and compact cameras. Source camera class identification scheme for DSLR and compact Cameras is proposed based on machine learning classifiers utilizing statistical features of wavelet sub-bands and noise residues. III Source Identification of Video through 6 Bit Replacement Advances of digital technology have brought us numerous cheap but good-quality imaging devices to capture the visionary signals into discrete form, i.e. digital images and videos.[15].With the increasing and fast proliferation and growing popularity, a security concern arises since electronic alteration on digital multimedia data for deceiving purposes becomes incredibly easy. Source identification is a major component of video forensics. Techniques such as the Watermarking, Resampling, Photo Response Non-Uniformity, Sensor Pattern Noise,etc are used for the identification of the video source. In this paper a new technique is implemented i.e identification of a source through a IP address. As most of the videos now a days are transmitted through the network so a new technique is established so as to identify the video and

ISSN: 2348 – 8387

System

Algorithm for embedding the IP, System Information, Video Information and MAC address.

Initially, select the carrier image from the video. Input the IP address, system information, video information, MAC address into image. Convert the IP address, system information, video information, MAC address into the binary format. Now sample the binary into Ns samples. Generate keys where length of key items is equal to the samples in binary. Read image pixels at the position I and extract Ip(i) of RGB. Now split the 8 bit RGB into (2+6) bits. Replace R(lsb) with sample Ns(i) , replace G(lsb) with Ns (i+1) and replace B(lsb) with sample Ns (i+2) repeat the steps from i=0 to length of key items. Convert RGB into their respective pixels Pi. .Now set the pixel Pi to image I. This is how the IP address, system information, video information and MAC address is hided into the into the image for the verifying the source of the video.

www.internationaljournalssrg.org

Page 130

Satellite Conference ICSTSD 2016 International Conference on Science and Technology for Sustainable Development, Kuala Lumpur, MALAYSIA, May 24-26, 2016

Entropy Mean of an image Std. Deviation of an image Pure Height Pure Width

Figure 1 Flow of 6 bit Replacement Algorithm

IV RESULT ANALYSIS As video identification plays a very vital role in a multimedia forensic department a new technique is established to identify the video through the IP. Initially, a video is taken which is to be authenticated. Frames and sound are extracted from that video. Digital signature is provided to the frames by embedding the IP address, system information, video information, MAC address in that particular frame which is to be authenticated. A digitally certified video is created from the frames from the digital signature. To verify that the video is authenticated or valid the digital certified the digital signature which is embedded is extracted and verified. In this way the IP address, video information and the system information is used to identify the source video.

Parameters Entropy Mean of an image Std. Deviation of an image Pure Height Pure Width

Table No. I Input Image 7.5071 127.7632 46.7939

IP Hidden Image 7.1653 134.94 40.3185

256 768

30 90

Image 7.1653 134.9485 40.3185

7.1653 134.9485 40.3185

30 90

30 90

Table No. IV IP Hidden Image and Extracted Image Mean Square Error 0 Peak Signal to Noise 99 Ratio Normalized Cross 1 Correlation Average Difference 0 Structural Content 1 Maximum Difference 0

Figure 2 Graphs

Parameters Entropy Mean of an image Std. Deviation of an image Pure Height Pure Width

Parameters

ISSN: 2348 – 8387

Table No. II Original Image 7.8078 129.9623 59.78431 256 768

Table No. III IP Hidden

Watermarked Image 7.8099 129.8957 59.8563 256 768

of Entropies

V CONCLUSION We have developed a new approach to the problem of video source identification. Our identification method uses the IP address to verify the source of the video along with the system information, video information and the Mac address of the system. This method gives a best result when the video is transmitted through the network. It gives a little helping hand to the forensic department where verifying a source So, with the help of this method the source of the video is identified along with the parameters like the system and the video information

Extracted Image

www.internationaljournalssrg.org

VI FUTURE SCOPE

Page 131

Satellite Conference ICSTSD 2016 International Conference on Science and Technology for Sustainable Development, Kuala Lumpur, MALAYSIA, May 24-26, 2016

Here, we have used the Avi formats videos to the verify the source identification but the compressed videos formats such as the MPEG, MPEG-5etc formats may also be used. As the video is transmitted through the network and while travelling through the network there may be blocking and blurring so, the videos containing the blocking and blurring should also be identified.

References [1]

J. Yang, H. Choi, and T. Kim, “Noise estimation for blocking artifacts reduction in DCT coded images,” IEEE Trans. Circuits Syst. Video Technol., vol. 10, no. 7, pp. 1116–1120, Oct. 2000. [2] Z. J. Geradts, J. Bijhold, M. Kieft, K. Kurosawa, K. Kuroki, and N. Saitoh, “Methods for identification of images acquired with digital cameras,” Proc. SPIE, Enabling Technol. Law Enforcement Secur., vol. 4232, pp. 505– 512, Feb. 2001. [3] J. Bellardo and S. Savage, “802.11 denial-of-service attacks: Real vulnerabilities and practical solutions,” in Proc. 12th Conf. USENIX Secur. Symp., 2003, pp. 15–28. [4] A. C. Popescu, “Statistical tools for digital image forensics,” Ph.D. dissertation, Dept. Comput. Sci., Dartmouth College, Hanover, NH, USA, 2004. [5] J. Lukáš, J. Fridrich, and M. Goljan, “Digital camera identification from sensor pattern noise,” IEEE Trans. Inf. Forensics Security, vol. 1, no. 2, pp. 205–214, Jun. 2006. [6] W. Wang and H. Farid, “Exposing digital forgeries in video by detecting double MPEG compression”, In Proc. ACM Multimedia and Security Workshop, pages 37–47, Geneva, Switzerland, 2006. [7] M. Chen, J. Fridrich, M. Goljan, and J. Lukáš, “Source digital camcorder identification using sensor photo response non-uniformity,” Proc. SPIE, Secur., Steganogr., Watermarking Multimedia Contents IX, vol. 6505, no. 1, p. 65051G, Feb. 2007. [8] Oya Çeliktutan, Bülent Sankur and Ismail Avcibas, “Blind Identification of Source Cell-Phone Model, IEEE Transactions On Information Forensics And Security, Vol. 3, No. 3, September 2008. [9] F. Lefebvre, B. Chupeau, A. Massoudi, and E. Diehl, “Image and video fingerprinting: Forensic applications,” Proc. SPIE, Media Forensics Secur., vol. 7254, pp. 1–9, Feb. 2009, [10]Yanmei Fang, Ahmet Emir Dirik, Xiaoxi Sun, Nasir Memon, “Source Class Identification for DSLR and Compact Cameras”, MMSP’09, October 57, 2009, Rio de Janeiro, Brazil. 978-1-4244-4464-9/09/$25.00 _c 2009 IEEE. [11] C.-T. Li, “Source camera identification using enhanced sensor pattern noise,” IEEE Trans. Inf. Forensics Security, vol. 5, no. 2, pp. 280–287, Jun. 2010. [12] Matthew C. Stamm, W. Sabrina Lin, K. J. Ray Liu, “Temporal Forensics and Anti-Forensics for Motion Compensated Video”, IEEE Transactions On Information Forensics And Security, Vol. 7, No. 4, August 2012. [13 ] Simone Milani, Marco Fontani, Paolo Bestagini, Mauro Barni, Alessandro Piva, Marco Tagliasacchi and Stefano Tubaro, “An overview on video forensics”, APSIPA Transactions on Signal and Information Processing , Volume 1 , August 2012. [14] Xiangui Kang, Yinxiang Li, Zhenhua Qu, and Jiwu Huang,“Enhancing Source Camera Identification Performance With a Camera Reference Phase Sensor Pattern Noise”, IEEE Transactions On Information Forensics And Security, VOL. 7, NO. 2, APRIL 2012. [15]Alex C. Kot and Hong Cao, “Image and Video Source Class

Identification”, Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore,2013 [16] T.Sathya, Ms.R.Raja kumari, R.Vinoth, “Implementation of Hardware for Source Identification using Pixel Non Uniformity Noise”, International Journal of Innovative Research in Science, Engineering and Technology ,volume 3, special issue 1, February 2014. [17] S. Chen, A. Pande, K. Zeng, and P. Mohapatra, “Video source identification in lossy wireless networks,” IEEE Transactions On Information Forensics And Security, Vol. 10, No. 1, January 2015. [18] Shweta P. Kachhawal ,Prof. Avinash P. Wadhe, “Study Of Different Video Forensics Techniques”, International Journal of Computer, Information Technology & Bioinformatics (IJCITB), ISSN: 2278-7593, Volume-2, Issue2. [19] Remya R.S, Busra Beevi , “A Novel Video Camera Authentication Based on Peak to Correlation Energy of Clustered Sensor Pattern Noise, IEEE International Conference on Engineering and Technology (ICETECH), 20th March 2015. [20] S. Chen, A. Pande, K. Zeng, and P. Mohapatra, “Video source identification in lossy wireless networks,” IEEE Transactions On Information Forensics And Security, Vol. 10, No. 1, January 2015. [21] Mustafa Al-Ani, Fouad Khelifi, Ashref Lawgaly, Ahmed Bouridane , “ A Novel Image Filtering Approach for Sensor Fingerprint Estimation in Source Camera Identification, EPSRC Research Grant (EP/L006812/1). [22] Nilambari Kulkarni, Vanita Mane, “ Source Camera Identification Using GLCM” IEEE International Advance Computing Conference (IACC),2015 [23]Naveen Sharma, Anwer Reyaz J, Balan C, “Video Source Identification,” / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 7 (1) , 2016, 363-366,ISSN:0975-9646,2016 [24] Monika R. Chourasiya, Prof. Avinash P Wadhe, “Video Forensic Frame Work For Video Source Identification –A Big Challenge To Video Forensic”, 5th International Conference On Quality Up-Gradation In Engineering , Science & Technology,IC-QUEST2016/CE22

AUTHOR PROFILE

Prof. Avinash P. Wadhe received the B.E from SGBAU Amravati University and MTech (CSE) From G.H Raisoni College of Engineering, Nagpur (an Autonomous Institute). He is currently Head of Department (CSE) in G.H Raisoni College of Engineering and Management, Amravati SGBAU Amravati University. His research interest includes Digital Forensics, Network Security, Data mining and Cloud Computing .He has contributed to more than 20 research papers. He had awarded with young investigator award in international conference.

Miss. Monika R. Chourasiya has completed her B.E from SGBAU Amravati University and she is presently pursuing

ISSN: 2348 – 8387

www.internationaljournalssrg.org

Page 132

Satellite Conference ICSTSD 2016 International Conference on Science and Technology for Sustainable Development, Kuala Lumpur, MALAYSIA, May 24-26, 2016

her Master of Engineering (CSE) from G.H. Raisoni College of Engineering and Management, Amravati SGBAU. Her research interest is Digital Forensics.

ISSN: 2348 – 8387

www.internationaljournalssrg.org

Page 133