Chris Pollett > Students >
Chang

    ( Print View)

    [Bio]

    [Blog]

    [CS297 Proposal]

    [Deliverable 1]

    [Deliverable 2]

    [Deliverable 3]

    [Deliverable 4]

    [CS 297 Report - PDF]

    [CS 298 Proposal]

    [CS 298 Report - PDF]

    [Defense Presentation Slides - PDF]

CS297 Proposal

Faking Sensor Noise Information.

Justin Chang (justin.h.chang@sjsu.edu)

Advisor: Dr. Chris Pollett

Description:

Pictures taken by digital cameras leave unique imprints on the images they produce. These imprints can be interpreted as noise and be passed through a filter. The goal of this project is to identify a noise filter and camera model pair and impose a noise pattern onto an image that is from a camera different than the camera that the image was originally taken from. This resulting image would be able to fool camera model detection networks of modern benchmarks.

Schedule:

Week 1: Aug 24 - Aug 31Search for Research Papers and work on Proposal
Week 2: Aug 31 - Sept 7Work on paper [1]
Week 3: Sept 7 - Sept 14Work on Del 1
Week 4: Sept 14 - Sept 21Finish work on Del 1
Week 5: Sept 21 - Sept 28Begin work on Del 2
Week 6: Sept 28 - Oct 5Continue to work on Del 2 and work on paper [2]
Week 7: Oct 5 - Oct 12Continue to work on Del 2
Week 8: Oct 12 - Oct 19Finish up Del 2
Week 9: Oct 19 - Oct 26Begin work on Del 3
Week 10: Oct 26 - Nov 2Finish work on Del 3
Week 11: Nov 2 - Nov 9Begin work on Del 4 and work on paper [3]
Week 12: Nov 9 - Nov 16Continue to work on Del 4 and work on paper [4]
Week 13: Nov 16 - Nov 23Finish work on Del 4
Week 14: Nov 23 - Nov 30Begin work on Del 5 and work on paper [5]
Week 15: Nov 30 - Dec 7Finish Del 5 and work on Final Report

Deliverables:

The full project will be done when CS298 is completed. The following will be done by the end of CS297:

1. Find dataset with images and labels with camera model names. Find sensor noise pattern for my own phone based on averages

2. Find sensor noise pattern for my own phone using wavelet transforms.

3. Look at existing camera model detection networks and test them against dataset.

4. Implement a GAN network.

5. Finish report.

References:

[1] J. Lukas, J. Fridrich and M. Goljan, "Digital camera identification from sensor pattern noise," in IEEE Transactions on Information Forensics and Security, vol. 1, no. 2, pp. 205-214, June 2006, doi: 10.1109/TIFS.2006.873602.

[2] D. Cozzolino and L. Verdoliva, "Noiseprint: A CNN-Based Camera Model Fingerprint," in IEEE Transactions on Information Forensics and Security, vol. 15, pp. 144-159, 2020, doi: 10.1109/TIFS.2019.2916364.

[3] S. Samaras, V. Mygdalis and I. Pitas, "Robustness in blind camera identification," 2016 23rd International Conference on Pattern Recognition (ICPR), 2016, pp. 3874-3879, doi: 10.1109/ICPR.2016.7900239.

[4] L. Bondi, L. Baroffio, D. Güera, P. Bestagini, E. J. Delp and S. Tubaro, "First Steps Toward Camera Model Identification With Convolutional Neural Networks," in IEEE Signal Processing Letters, vol. 24, no. 3, pp. 259-263, March 2017, doi: 10.1109/LSP.2016.2641006.

[5] R. Li, Y. Guan and C. Li, "PCA-based denoising of Sensor Pattern Noise for source camera identification," 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP), 2014, pp. 436-440, doi: 10.1109/ChinaSIP.2014.6889280.