Smartphone Video Source Identification Based on Sensor Pattern Noise

Authors: Raquel Ramos López, Anissa El-Khattabi, Ana Lucila Sandoval Orozco, Luis Javier García Villalba

Abstract:

An increasing number of mobile devices with integrated cameras has meant that most digital video comes from these devices. These digital videos can be made anytime, anywhere and for different purposes. They can also be shared on the Internet in a short period of time and may sometimes contain recordings of illegal acts. The need to reliably trace the origin becomes evident when these videos are used for forensic purposes. This work proposes an algorithm to identify the brand and model of mobile device which generated the video. Its procedure is as follows: after obtaining the relevant video information, a classification algorithm based on sensor noise and Wavelet Transform performs the aforementioned identification process. We also present experimental results that support the validity of the techniques used and show promising results.

Keywords: Digital video, forensics analysis, key frame, mobile device, PRNU, sensor noise, source identification.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1130585

References:

[1] Alexa Internet, Inc., “Alexa Top 500 Global Sites,” goo.gl/XyQWaE, 2016.
[2] I. Gartner, “Gartner Says Annual Smartphone Sales Surpassed Sales of Feature Phones for the First Time in 2013,” https://goo.gl/4GbxiB, 2014.
[3] I. IC Insights, “Embedded Imaging Takes Off as Stand-alone Digital Cameras Stall,” goo.gl/lpuWg9, 2014.
[4] C. Wen and K. Yang, “Image authentication for digital image evidence,” Forensic Science Journal, vol. 5, no. 1, pp. 1–11, September 2006.
[5] P. Brown, “Searches of Cell Phones Incident to Arrest: Overview of the Law as it Stands and a New Path Forward,” Harvard Journal of Law & Technology, vol. 27, pp. 563–587, 2014.
[6] P. Bestagini, M. Fontani, S. Milani, M. Barni, A. Piva, M. Tagliasacchi, and S. Tubaro, “An overview on video forensics,” in Proceedings of the 20th European Signal Processing Conference, August 2012, pp. 1229–1233.
[7] A. L. Sandoval Orozco, D. M. Arenas Gonz´alez, J. Rosales Corripio, L. J. Garc´ıa Villalba, and J. C. Hernandez-Castro, “Techniques for Source Camera Identification,” in Proceedings of the 6th International Conference on Information Technology, May 2013, pp. 1–9.
[8] J. Lukas, J. Fridrich, and M. Goljan, “Digital Camera Identification from Sensor Pattern Noise,” IEEE Transactions on Information Forensics and Security, vol. 1, no. 2, pp. 205–214, June 2006.
[9] C. Li, “Source Camera Identification Using Enhanced Sensor Pattern Noise,” IEEE Transactions on Information Forensics and Security, vol. 5, no. 2, pp. 280–287, June 2010.
[10] A. Wahab, A. Ho, and S. Li, “Inter-Camera Model Image Source Identification with Conditional Probability Features,” in Proceedings of IIEEJ 3rd Image Electronics and Visual Computing Workshop, November 2012, pp. 1–4.
[11] A. Wahab, J. Briffa, H. Schaathun, and A. T. S. Ho, “Conditional Probability Based Steganalysis for JPEG Steganography,” in Proceedings of the International Conference on Signal Processing Systems, May 2009, pp. 205–209.
[12] D. M. Arenas Gonz´alez, A. L. Sandoval Orozco, J. Rosales Corripio, L. J. Garc´ıa Villalba, J. Hernandez-Castro, and S. J. Gibson, “Proceedings of the Source Smartphone Identification Using Sensor Pattern Noise and Wavelet Transform,” in Proceedings of the 5th International Conference on Imaging for Crime Detection and Prevention, 16-17 December 2013, pp. 1–6.
[13] Y. Su, J. Xu, and B. Dong, “A Source Video Identification Algorithm Based on Motion Vectors,” in Proceedings of the Second International Workshop on Computer Science and Engineering, vol. 2, October 2009, pp. 312–316.
[14] S. Yahaya, A. Ho, and A. Wahab, “Advanced video camera identification using Conditional Probability Features,” in Proceedings of the IET Conference on Image Processing, July 2012, pp. 1–5.