Abstract
Ensuring the legitimacy of image information is one of the critical issues for smooth operation of web systems such as Internet auctions. Linking the image to its source camera would be helpful to detect malicious activities on the web. This paper presents a secure pairing framework that utilizes Photo-Response Non-Uniformity (PRNU), a unique fingerprint of imaging sensors imprinted in a photo, for reliable source camera identification. However, the recent studies have found the image acquisition process of each camera model also leaves its unique pattern in the images, which could disturb the PRNU extraction and lead to the accuracy impairment. This is a serious issue since many people are using the same model smartphones in the real world. To address this issue, we propose to expand the traditional binary Same/Different device classification to a triplet classification by (1) different model (i.e. different device), (2) same model different device, and (3) same model same device. We also present two simple but effective defensive methods to tackle against a fingerprint-copy attack which aims at falsifying the device identification, and an attack with image manipulations. Results on a well-known benchmark dataset prove our proposed method can deliver high device identification accuracy, as well as robustness to spoofing attacks and image forgeries.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ba, Z., Piao, S., Fu, X., Koutsonikolas, D., Mohaisen, A., Ren, K.: Abc: enabling smartphone authentication with built-in camera. In: 25th Annual Network and Distributed System Security Symposium, NDSS 2018 (2018)
Bruno, A., Cattaneo, G., Capasso, P.: On the reliability of the PNU for source camera identification tasks. arXiv preprint arXiv:2008.12700 (2020)
Chen, M., Fridrich, J., Goljan, M., Lukás, J.: Determining image origin and integrity using sensor noise. IEEE Trans. Inf. Forensics Secur. 3(1), 74–90 (2008)
Cozzolino, D., Marra, F., Gragnaniello, D., Poggi, G., Verdoliva, L.: Combining PNU and noise print for robust and efficient device source identification. EURASIP J. Inf. Secur. 2020(1), 1–12 (2020)
Cozzolino, D., Verdoliva, L.: Noiseprint: a CNN-based camera model fingerprint. arXiv preprint arXiv:1808.08396 (2018)
Freire-Obregón, D., Narducci, F., Barra, S., Castrillón-Santana, M.: Deep learning for source camera identification on mobile devices. Patt. Recogn. Lett. 126, 86–91 (2019)
Gloe, T., Böhme, R.: The ‘Dresden image database’ for benchmarking digital image forensics. In: Proceedings of the 2010 ACM Symposium on Applied Computing, pp. 1584–1590 (2010)
Goljan, M., Fridrich, J., Chen, M.: Defending against fingerprint-copy attack in sensor-based camera identification. IEEE Trans. Inf. Forensics Secur. 6(1), 227–236 (2010)
Iuliani, M., Fontani, M., Piva, A.: A leak in PRNU based source identification? questioning fingerprint uniqueness. arXiv preprint arXiv:2009.04878 (2020)
Kirchner, M., Johnson, C.: SPN-CNN: boosting sensor-based source camera attribution with deep learning. In: 2019 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1–6. IEEE (2019)
Korus, P., Huang, J.: Multi-scale analysis strategies in PRNU-based tampering localization. IEEE Trans. Inf. Forensics Secur. 12(4), 809–824 (2016)
Li, H., Luo, W., Rao, Q., Huang, J.: Anti-forensics of camera identification and the triangle test by improved fingerprint-copy attack. arXiv preprint arXiv:1707.07795 (2017)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Lukas, J., Fridrich, J., Goljan, M.: Digital camera identification from sensor pattern noise. IEEE Trans. Inf. Forensics Secur. 1(2), 205–214 (2006)
Mandelli, S., Cozzolino, D., Bestagini, P., Verdoliva, L., Tubaro, S.: Cnn-based fast source device identification. IEEE Sig. Proces. Lett. 27, 1285–1289 (2020)
Mayer, O., Stamm, M.C.: Forensic similarity for digital images. IEEE Trans. Inf. Forensics Secur. 15, 1331–1346 (2019)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Shullani, D., Fontani, M., Iuliani, M., Al Shaya, O., Piva, A.: Vision: a video and image dataset for source identification. EURASIP J. Inf. Secur. 2017(1), 1–16 (2017)
Suzuki, S., et al.: Topological structural analysis of digitized binary images by border following. Comput. Vis. Graph. Image Process. 30(1), 32–46 (1985)
Villalba, L.J.G., Orozco, A.L.S., Corripio, J.R., Hernandez-Castro, J.: A PRNU-based counter-forensic method to manipulate smartphone image source identification techniques. Fut. Gene. Comput. Syst. 76, 418–427 (2017)
Yao, H., Qiao, T., Xu, M., Zheng, N.: Robust multi-classifier for camera model identification based on convolution neural network. IEEE Access 6, 24973–24982 (2018)
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Free-form image inpainting with gated convolution. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4471–4480 (2019)
Zhang, W., Tang, X., Yang, Z., Niu, S.: Multi-scale segmentation strategies in PRNU-based image tampering localization. Multim. Tools Appl. 78(14), 20113–20132 (2019)
Zhou, P., Han, X., Morariu, V.I., Davis, L.S.: Learning rich features for image manipulation detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1053–1061 (2018)
Acknowledgement
We would like to thank Entrupy Inc. for providing data and Satsuya Ohata for his feedback and discussion.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hsiao, A., Takenouchi, T., Kikuchi, H., Sakiyama, K., Miura, N. (2022). More Accurate and Robust PRNU-Based Source Camera Identification with 3-Step 3-Class Approach. In: Zhao, X., Piva, A., Comesaña-Alfaro, P. (eds) Digital Forensics and Watermarking. IWDW 2021. Lecture Notes in Computer Science(), vol 13180. Springer, Cham. https://doi.org/10.1007/978-3-030-95398-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-95398-0_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95397-3
Online ISBN: 978-3-030-95398-0
eBook Packages: Computer ScienceComputer Science (R0)