VISION: a video and image dataset for source identification
Tóm tắt
Forensic research community keeps proposing new techniques to analyze digital images and videos. However, the performance of proposed tools are usually tested on data that are far from reality in terms of resolution, source device, and processing history. Remarkably, in the latest years, portable devices became the preferred means to capture images and videos, and contents are commonly shared through social media platforms (SMPs, for example, Facebook, YouTube, etc.). These facts pose new challenges to the forensic community: for example, most modern cameras feature digital stabilization, that is proved to severely hinder the performance of video source identification technologies; moreover, the strong re-compression enforced by SMPs during upload threatens the reliability of multimedia forensic tools. On the other hand, portable devices capture both images and videos with the same sensor, opening new forensic opportunities. The goal of this paper is to propose the VISION dataset as a contribution to the development of multimedia forensics. The VISION dataset is currently composed by 34,427 images and 1914 videos, both in the native format and in their social version (Facebook, YouTube, and WhatsApp are considered), from 35 portable devices of 11 major brands. VISION can be exploited as benchmark for the exhaustive evaluation of several image and video forensic tools.
Tài liệu tham khảo
Statista Inc., Statista. http://www.statista.com/statistics/263437/global-smartphone-sales-to-end-users-since-2007/. Accessed 22 Sept 2017.
A De Rosa, A Piva, M Fontani, M Iuliani, in 2014 International Carnahan Conference on Security Technology (ICCST). Investigating multimedia contents (IEEE, Rome, 2014), pp. 1–6.
A Piva, An overview on image forensics. ISRN Signal Proc. 2013:, 496701–22 (2013).
M Iuliani, M Fontani, D Shullani, A Piva, A hybrid approach to video source identification. arXiv:1705.01854[cs.MM] (2017).
J Lukas, J Fridrich, M Goljan, Digital camera identification from sensor pattern noise. IEEE Trans. Inf. Forensic Secur. 1(2), 205–214 (2006).
W Van Houten, Z Geradts, Source video camera identification for multiply compressed videos originating from youtube. Digit. Investig. 6(1), 48–60 (2009).
M Chen, J Fridrich, M Goljan, J Lukáš, in Proc. of SPIE 6515 Electronic Imaging 2007. Source digital camcorder identification using sensor photo response non-uniformity, (2007), pp. 65051–65051. International Society for Optics and Photonics.
W-H Chuang, H Su, M Wu, in IEEE International Conference on Image Processing (ICIP). Exploring compression effects for improved source camera identification using strongly compressed video (IEEE, Brussels, 2011), pp. 1953–1956.
S Chen, A Pande, K Zeng, P Mohapatra, Live video forensics: source identification in lossy wireless networks. IEEE Trans. Inf. Forensic Secur. 10(1), 28–39 (2015).
G Schaefer, M Stich, in Proc. SPIE 5307 Electronic Imaging 2004. Ucid: an uncompressed color image database, (2003), pp. 472–480. International Society for Optics and Photonics.
T Gloe, R Böhme, The Dresden image database for benchmarking digital image forensics. J. Digit. Forensic Pract. 3(2-4), 150–159 (2010).
T Gloe, R Böhme, in Proceedings of the 25th Symposium On Applied Computing (ACM SAC 2010), 2. The ‘Dresden Image Database’ for benchmarking digital image forensics (ACM New York, Sierre, 2010), pp. 1585–1591.
D-T Dang-Nguyen, C Pasquini, V Conotter, G Boato, in Proceedings of the 6th ACM Multimedia Systems Conference. MMSys ’15. Raise: a raw images dataset for digital image forensics (ACM, New York, 2015), pp. 219–224.
D Vázquez-Padín, F Pérez-González, in 2011 IEEE International Workshop on Information Forensics and Security. Prefilter design for forensic resampling estimation (IEEE, Iguacu Falls, 2011), pp. 1–6.
G Qadir, S Yahaya, ATS Ho, in Proceedings of the IET IPR 2012, 3-4 July, London. Surrey University Library for Forensic Analysis (SULFA), (2012).
L D’Amiano, D Cozzolino, G Poggi, L Verdoliva, in Multimedia & Expo Workshops (ICMEW), 2015 IEEE International Conference On. Video forgery detection and localization based on 3d patchmatch (IEEE, Turin, 2015), pp. 1–6.
OI Al-Sanjary, AA Ahmed, G Sulong, Development of a video tampering dataset for forensic investigation. Forensic Sci. Int. 266:, 565–572 (2016).
F Bertini, R Sharma, A Iannı, D Montesi, MA Zamboni, in The International Conference on Computing Technology, Information Security and Risk Management (CTISRM2016). Social media investigations using shared photos (Dubai, 2016), p. 47.
M Moltisanti, A Paratore, S Battiato, L Saravo, in Image Analysis and Processing - ICIAP 2015 - 18th International Conference, Genoa, Italy, September 7-11, 2015, Proceedings, Part II. Image manipulation on facebook for forensics evidence (Springer Genoa, 2015), pp. 506–517.
Z Wang, AC Bovik, HR Sheikh, EP Simoncelli, Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004).
D Bolton, youtube-dl documentation. github.com/rg3/youtube-dl/blob/master/README.md#readme. Accessed 22 Sept 2017.
M Chen, J Fridrich, M Goljan, J Lukáš, Determining image origin and integrity using sensor noise. IEEE Trans. Inf. Forensic Secur. 3(1), 74–90 (2008).
M Goljan, J Fridrich, T Filler, in Publisher: Proc. SPIE 7254 IS&T/SPIE Electronic Imaging. Large scale test of sensor fingerprint camera identification, (2009), pp. 72540–72540. International Society for Optics and Photonics.
S Taspinar, M Mohanty, N Memon, in 2016 IEEE International Workshop on Information Forensics and Security (WIFS). Source camera attribution using stabilized video (IEEE, Abu Dhabi, 2016), pp. 1–6.
M Goljan, J Fridrich, Camera identification from scaled and cropped images. Secur. Forensic Steganography Watermarking Multimedia Contents X. 6819:, 68190 (2008).
D Shullani, O Al Shaya, M Iuliani, M Fontani, A Piva, in Proceeding of 2017 Tyrrhenian International Workshop on Digital Communications, Communications in Computer and Information Science, vol. 766, September 18–20, 2017, Palermo. A Dataset for forensic analysis of videos in the wild, (2017), pp. 84–94.