Asia pacific journal of information systems

The Korea Society of Management Information Systems (한국경영정보학회)
권호 표지
DOI QR코드

DOI QR Code

Attack Detection on Images Based on DCT-Based Features

  • Nirin Thanirat (Faculty of Information and Communication Technology, Mahidol University) ;
  • Sudsanguan Ngamsuriyaroj (Faculty of Information and Communication Technology, Mahidol University)
  • Received : 2021.02.06
  • Accepted : 2021.07.14
  • Published : 2021.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

As reproduction of images can be done with ease, copy detection has increasingly become important. In the duplication process, image modifications are likely to occur and some alterations are deliberate and can be viewed as attacks. A wide range of copy detection techniques has been proposed. In our study, content-based copy detection, which basically applies DCT-based features for images, namely, pixel values, edges, texture information and frequency-domain component distribution, is employed. Experiments are carried out to evaluate robustness and sensitivity of DCT-based features from attacks. As different types of DCT-based features hold different pieces of information, how features and attacks are related can be shown in their robustness and sensitivity. Rather than searching for proper features, use of robustness and sensitivity is proposed here to realize how the attacked features have changed when an image attack occurs. The experiments show that, out of ten attacks, the neural networks are able to detect seven attacks namely, Gaussian noise, S&P noise, Gamma correction (high), blurring, resizing (big), compression and rotation with mostly related to their sensitive features.

Keywords

References

  1. Al-Qershi, O. M., and Khoo, B. E. (2013). Passive detection of copy-move forgery in digital images: State-of-the-art. Forensic science international, 231 (1-3), 284-295. https://doi.org/10.1016/j.forsciint.2013.05.027
  2. Angelides, M. C., and Agius, H. (2010). The Handbook of MPEG applications. John Wiley & Sons, Ltd, Chichester, UK.
  3. Arnia, F., Fujiyoshi, M., and Kiya, H. (2007). The use of DCT coefficient sign for content-based copy detection. 2007 International Symposium on Communications and Information Technologies, 1476-1481.
  4. Arnia, F., Munadi, K., Fujiyoshi, M., and Kiya, H. (2009). Efficient content-based copy detection using signs of DCT coefficient. 2009 IEEE Symposium on Industrial Electronics & Applications, 494-499.
  5. California Institute of Technology: Caltech-UCSD Birds 200. Available from http://www.vision.caltech.edu/visipedia/CUB-200.html (Accessed 2017-3-14).
  6. California Institute of Technology: Computational Vision: Archive. Available from http://www.vision.caltech.edu/html-files/archive.html (Accessed 2017-3-14).
  7. Cao, Y., Gao, T., Fan, L., and Yang, Q. (2012). A robust detection algorithm for copy-move forgery in digital images. Forensic Science International, 214(1-3), 33-43. https://doi.org/10.1016/j.forsciint.2011.07.015
  8. Chen, J. (2010). Detection of video copies based on robust descriptors. The 2010 International Conference on Apperceiving Computing and Intelligence Analysis Proceeding, 303-306.
  9. Chiu, C. Y., Chen, C. S., and Chien, L. F. (2008). A framework for handling spatiotemporal variations in video copy detection. IEEE Transactions on Circuits and Systems for Video Technology, 18(3), 412-417. https://doi.org/10.1109/TCSVT.2008.918447
  10. Cieplinski, L. (2001). MPEG-7 color descriptors and their applications. Computer Analysis of Images and patterns, 7, 11-20. https://doi.org/10.1007/3-540-44692-3_3
  11. Eom, M., and Choe, Y. (2007). Fast extraction of edge histogram in DCT domain based on MPEG7. World Academy of Science Engineering and Technology International Journal of Computer and Information Engineering, 1(9), 1397-1400.
  12. Fadeev, A., and Frigui, H. (2008). Dominant Texture Descriptors for image classification and retrieval. 2008 15th IEEE International Conference on Image Processing, 989-992.
  13. Gonzalez, R. C., and Woods, R. E. (1992). Digital image processing (2nd edition). Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA.
  14. Jegou, H., Douze, M., and Schmid, C. (2008). Hamming embedding and weak geometry consistency for large scale image search. Proceedings of the 10th European conference on Computer vision. Available from http://lear.inrialpes.fr/-jegou/data.php
  15. Jiang, J., Qiu, K., and Xiao, G. (2008). A block-edge-pattern-based content descriptor in DCT domain. IEEE Transactions on Circuits and Systems for Video Technology, 18(7), 994-998.
  16. Kasutani, E., and Yamada, A. (2001). The MPEG-7 color layout descriptor: A compact image feature description for high-speed image/video segment retrieval. Proceedings 2001 International Conference on Image Processing, 1, 674-677.
  17. Kim, C. (2003). Content-based image copy detection. Signal Processing: Image Communication, 18(3), 169-184. https://doi.org/10.1016/S0923-5965(02)00130-3
  18. Li, Z., and Chen, J. (2010). Efficient compressed domain video copy detection. 2010 International Conference on Management and Service Science, 1-4.
  19. Li, Z., and Tan, Y. P. (2006). Content-based video copy detection with video signature. 2006 IEEE International Symposium on Circuits and Systems, 4321-4324.
  20. Massoudi, A., Lefebvre, F., Demarty, C. H., Oisel, L., and Chupeau, B. (2006). A video fingerprint based on visual digest and local fingerprints. 2006 International Conference on Image Processing, 2297-2300.
  21. Pandey, R. C., Singh, S. K., and Shukla, K. K. (2016). Passive forensics in image and video using noise features: A review. Digital Investigation, 19, 1-28. https://doi.org/10.1016/j.diin.2016.08.002
  22. Roopalakshmi, R., Reddy, G., and Ram M. (2011). A novel approach to video copy detection using audio fingerprints and PCA. Procedia Computer Science, 5, 149-156. https://doi.org/10.1016/j.procs.2011.07.021
  23. Roopalakshmi, R., Reddy, G., and Ram, M. (2010). Recent trends in content-based video copy detection. 2010 IEEE International Conference on Computational Intelligence and Computing Research, 1-5.
  24. Rosenberg, Chuck. The Lenna Story - www.lenna.org. Available from https://www.cs.cmu.edu/-chuck/lennapg/ (Accessed 2017-3-14).
  25. Skrepth C. J., and Uhl, A. (2003). Robust hash functions for visual data: An experimental comparison. In: Perales F.J., Campilho A.J.C., de la Blanca N.P., Sanfeliu A. (eds) Pattern Recognition and Image Analysis. IbPRIA 2003. Lecture Notes in Computer Science, vol. 2652. Springer, Berlin, Heidelberg.
  26. Wu, M. N., Lin, C. C., and Chang, C. C. (2007). Novel image copy detection with rotating tolerance. Journal of Systems and Software, 80(7), 1057-1069. https://doi.org/10.1016/j.jss.2006.12.001
  27. Xu, Z., Ling, H., Zou, F., Lu, Z., Li, P., and Wang, T. (2009). Fast and robust video copy detection scheme using full DCT coefficients. 2009 IEEE International Conference on Multi-media and Expo, 434-437.
  28. Yang, R., Tian, Y., and Huang, T. (2009). DCT-based video-printing on saliency-consistent regions for detecting video copies with text insertion, Advances in Multimedia Information Processing - PCM 2009. Lecture Notes in Computer Science, 5879, 797-806.
  29. Ye, J. (2011). Cosine similarity measures for intuitionistic fuzzy sets and their applications. Mathematical and Computer Modelling, 53(1-2), 91-97. https://doi.org/10.1016/j.mcm.2010.07.022
  30. Zhang, Z., and Yuan, F. (2010). Compressed video copy detection based on texture analysis. 2010 IEEE International Conference on Wireless Communications, Networking and Information Security, 612-615.
  31. Zhang, Z., and Zou, J. (2010). Compressed video copy detection based on edge analysis. The 2010 IEEE International Conference on Information and Automation, 2497-2501.
  32. Zhang, Z., Zhang, R., and Cao, C. (2010). Video copy detection based on temporal features of key frames. 2010 International Conference on Artificial Intelligence and Education, 627-630.