Lightweight Photo-Response Non-Uniformity Fingerprint Extraction Algorithm Based on an Invertible Denoising Network
Source abstract
Abstract
The photo-response non-uniformity (PRNU) noise of imaging sensors significantly aids digital forensics and judicial identification, as it can be used as the fingerprint for uniquely identifying individual imaging devices. During the PRNU fingerprint extraction, it is very important for source camera identification to estimate the natural noise from real-world images. Most existing deep learning-based neural networks have a large number of model parameters, and they may not be practical in realistic scenarios such as deploying the model on small devices like smartphones and remote forensics equipment. In this paper, we present a lightweight PRNU fingerprint extraction algorithm based on an invertible denoising network (InvDN) for source camera identification. Specifically, to reduce the number of parameters, the deep network uses a constant amount of memory to compute the gradient and employs the same parameters for both forward and backward propagation. In addition, by introducing an information-loss-less reversible network, more complete PRNU fingerprint information can be extracted. Experimental results show that this algorithm exhibits superior PRNU fingerprint extraction performance and generalization ability compared to the state-of-the-art PRNU fingerprint extraction algorithms.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Digital Media Forensic Detection · Image and Signal Denoising Methods · Advanced Steganography and Watermarking Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of National Security, People’s Public Security University of China, Beijing 100038, China
Funding
Ministry of Public Security Science and Technology Plan Technical Research Project · Fundamental Research Funds for the Central Universities
References (22)
Show source-provided references
1. Digital camera identification from sensor pattern noise10.1109/TIFS.2006.873602 ↗
2. Cortiana, A., Conotter, V., Boato, G., and De Natale, F.G.B. (2011, January 23–27). Performance comparison of denoising filters for source camera identification. Proceedings of the IS&T/SPIE Electronic Imaging, San Francisco, CA, USA.10.1117/12.872489 ↗
3. Goljan, M., Fridrich, J., and Filler, T. (2009, January 18–22). Large scale test of sensor fingerprint camera identification. Media forensics and security. Proceedings of the IS&T/SPIE Electronic Imaging, San Jose, CA, USA.10.1117/12.805701 ↗
4. Jain, V., and Seung, H.S. (2008, January 8–11). Natural image denoising with convolutional networks. Proceedings of the Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada.
5. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising10.1109/TIP.2017.2662206 ↗
6. Burger, H.C., Schuler, C.J., and Harmeling, S. (2012, January 16–21). Image denoising: Can plain neural networks compete with BM3D?. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.10.1109/CVPR.2012.6247952 ↗
7. Prnu extraction algorithm based on tripartite weighted sparse coding model
8. Prnu extraction algorithm combined with deep iterative down-up cnn model
9. Image camera fingerprint extraction algorithm based on mprnet
10. Effective PRNU extraction via densely connected hierarchical network10.1007/s11042-022-12507-w ↗
11. Liu, Y., Qin, Z., Anwar, S., Ji, P., Kim, D., Caldwell, S., and Gedeon, T. (2021, January 20–25). Invertible denoising network: A light solution for real noise removal. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021, Nashville, TN, USA.10.1109/CVPR46437.2021.01316 ↗
12. Kay, S.M. (1993). Fundamentals of Statistical Signal Processing: Estimation Theory, Prentice-Hall, Inc.
13. Kingsbury, N., and Magarey, J. (1998). Wavelet Transforms in Image Processing, Birkhäuser.10.1007/978-1-4612-1768-8_2 ↗
14. Dinh, L., Sohl-Dickstein, J., and Bengio, S. (2016). Density estimation using Real NVP. arXiv.
15. Gomez, A.N., Ren, M., Urtasun, R., and Grosse, R.B. (2017, January 4–9). The reversible residual network: Backpropagation without storing activations. Proceedings of the Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA.
16. Yue, Z., Yong, H., Zhao, Q., Meng, D., and Zhang, L. (2008, January 8–11). Variational denoising network: Toward blind noise modeling and removal. Proceedings of the Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada.
17. Yue, Z., Zhao, Q., Zhang, L., and Meng, D. (2020, January 23–28). Dual adversarial network: Toward real-world noise removal and noise generation. Proceedings of the Computer Vision–ECCV 2020: 16th European CONFERENCE, Glasgow, UK. Proceedings, Part X 16.10.1007/978-3-030-58607-2_3 ↗
18. Liu, Y., Qin, Z., Anwar, S., Caldwell, S., and Gedeon, T. (2020, January 23–27). Are deep neural architectures losing information? Invertibility is indispensable. Proceedings of the Neural Information Processing: 27th International Conference, ICONIP 2020, Bangkok, Thailand. Proceedings, Part III 27.10.1007/978-3-030-63836-8_15 ↗
19. Daxing smartphone identification dataset10.1109/ACCESS.2019.2928356 ↗
20. Gloe, T., and Böhme, R. (2010, January 22–26). The dresden image database for benchmarking digital image forensics. Proceedings of the 2010 ACM Symposium on Applied Computing, Sierre, Switzerland.10.1145/1774088.1774427 ↗
21. Martín-Rodríguez, F., Isasi-de-Vicente, F., and Fernández-Barciela, M. (2023). A Stress Test for Robustness of Photo Response Nonuniformity (Camera Sensor Fingerprint) Identification on Smartphones. Sensors, 23.10.20944/preprints202302.0003.v1 ↗
22. Overview of passive forensics and anti-forensics techniques for GAN-gen-erated image