Smartphone Video Source Identification Based on Sensor Pattern Noise

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.

Authors:

• Raquel Ramos López
• Anissa El-Khattabi
• Ana Lucila Sandoval Orozco
• Luis Javier García Villalba

Keywords:

• Digital video
• forensics analysis
• key frame
• mobile device
• PRNU
• sensor noise
• source identification.

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.