Broadcasting and Media Magazine (방송과미디어)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지

딥러닝 기반 영상 조작 및 검출 기술 동향

  • Published : 2022.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

다양한 목적으로 영상을 조작하려는 시도는 디지털 영상이 보편화되기 시작할 때부터 지속적으로 존재해 왔던 문제이며, 이러한 영상 조작의 유무를 검출하려는 시도 또한 지난 수십 년 동안 끊임없이 연구되어 왔다. 최근 빠르게 발전하는 인공지능 기술, 그 중에서도 딥러닝 기술을 이용하여 영상 조작을 검출하는 기술이 다양하게 발전되고 있지만, 한편으로는 딥러닝 기술을 이용하여 조작을 보다 정교하게 진행하거나 검출을 회피하려는 기술 또한 빠르게 발전하고 있다. 본 고에서는 영상을 조작하고, 검출하고 회피하는 기술 동향에 대하여 종합적으로 소개하고, 특히 딥러닝 기반의 기술이 각각의 영역에서 어떻게 적용되고 발전하고 있는지에 대하여 면밀히 살펴보고자 한다.

Keywords

References

  1. Piva, Alessandro. "An overview on image forensics." International Scholarly Research Notices (2013).
  2. Milani, Simone, et al. "An overview on video forensics." APSIPA Transactions on Signal and Information Processing (2012).
  3. Yang, Pengpeng, et al. "A survey of deep learning-based source image forensics." Journal of Imaging 6.3 (2020): 9. https://doi.org/10.3390/jimaging6030009
  4. Castillo Camacho, Ivan, and Kai Wang. "A Comprehensive review of deep-Learning-based methods for image forensics." Journal of Imaging 7.4 (2021): 69. https://doi.org/10.3390/jimaging7040069
  5. Filler, Tomas, Jessica Fridrich, and Miroslav Goljan. "Using sensor pattern noise for camera model identification." 2008 15th IEEE International Conference on Image Processing. IEEE, 2008.
  6. Ferrara, Pasquale, et al. "Image forgery localization via fine-grained analysis of CFA artifacts." IEEE Transactions on Information Forensics and Security 7.5 (2012): 1566-1577. https://doi.org/10.1109/TIFS.2012.2202227
  7. Li, Bin, Yun Q. Shi, and Jiwu Huang. "Detecting doubly compressed JPEG images by using mode based first digit features." 2008 IEEE 10th Workshop on Multimedia Signal Processing. IEEE, 2008.
  8. Li, Jixian, et al. "Double JPEG compression detection based on block statistics." Multimedia Tools and Applications 77.24 (2018): 31895-31910. https://doi.org/10.1007/s11042-018-6175-2
  9. Jiang, Xinghao, et al. "Detection of double compression in MPEG-4 videos based on Markov statistics." IEEE Signal processing letters 20.5 (2013): 447-450. https://doi.org/10.1109/LSP.2013.2251632
  10. Huang, Fangjun, Jiwu Huang, and Yun Qing Shi. "Detecting double JPEG compression with the same quantization matrix." IEEE Transactions on Information Forensics and Security 5.4 (2010): 848-856. https://doi.org/10.1109/TIFS.2010.2072921
  11. Huang, Xiaosa, Shilin Wang, and Gongshen Liu. "Detecting double JPEG compression with same quantization matrix based on dense CNN feature." 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018.
  12. Bakas, Jamimamul, Anil Kumar Bashaboina, and Ruchira Naskar. "MPEG double compression based intra-frame video forgery detection using CNN." 2018 International Conference on Information Technology (ICIT). IEEE, 2018.
  13. Hong, Jin Hyung, Yoonmo Yang, and Byung Tae Oh. "Detection of frame deletion in HEVC-Coded video in the compressed domain." Digital Investigation 30 (2019): 23-31. https://doi.org/10.1016/j.diin.2019.06.002
  14. Jiang, Xinghao, et al. "Detection of HEVC double compression with the same coding parameters based on analysis of intra coding quality degradation process." IEEE Transactions on Information Forensics and Security 15 (2019): 250-263. https://doi.org/10.1109/tifs.2019.2918085
  15. Uddin, Kutub, Yoonmo Yang, and Byung Tae Oh. "Double compression detection in HEVC-coded video with the same coding parameters using picture partitioning information." Signal Processing: Image Communication (2022): 116638.
  16. Zhang, Xu, Svebor Karaman, and Shih-Fu Chang. "Detecting and simulating artifacts in GAN fake images." 2019 IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, 2019.
  17. Qian, Yuyang, et al. "Thinking in frequency: Face forgery detection by mining frequency-aware clues." European Conference on Computer Vision. Springer, Cham, 2020.
  18. Frank, Joel, et al. "Leveraging frequency analysis for deep fake image recognition." International Conference on Machine Learning. PMLR, 2020.
  19. Wang, Sheng-Yu, et al. "CNN-generated images are surprisingly easy to spot... for now." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020.
  20. Zampoglou, Markos, Symeon Papadopoulos, and Yiannis Kompatsiaris. "Detecting image splicing in the wild (web)." 2015 IEEE International Conference on Multimedia & Expo Workshops. IEEE, 2015.
  21. Korus, Pawe l, and Jiwu Huang. "Multi-scale analysis strategies in PRNU-based tampering localization." IEEE Transactions on Information Forensics and Security 12.4 (2016): 809-824. https://doi.org/10.1109/TIFS.2016.2636089
  22. Guan, Haiying, et al. "MFC datasets: Large-scale benchmark datasets for media forensic challenge evaluation." 2019 IEEE Winter Applications of Computer Vision Workshops. IEEE, 2019.
  23. Rossler, Andreas, et al. "Faceforensics++: Learning to detect manipulated facial images." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.
  24. Kang, Xiangui, et al. "Robust median filtering forensics using an autoregressive model." IEEE Transactions on Information Forensics and Security 8.9 (2013): 1456-1468. https://doi.org/10.1109/TIFS.2013.2273394
  25. Kirchner, Matthias, and Rainer Bohme. "Hiding traces of resampling in digital images." IEEE Transactions on Information Forensics and Security 3.4 (2008): 582-592. https://doi.org/10.1109/TIFS.2008.2008214
  26. Qureshi, Muhammad Ali, and El-Sayed M. El-Alfy. "Bibliography of digital image anti-forensics and anti-anti-forensics techniques." IET Image Processing 13.11 (2019): 1811-1823. https://doi.org/10.1049/iet-ipr.2018.6587
  27. Kim, Dongkyu, et al. "Median filtered image restoration and anti-forensics using adversarial networks." IEEE Signal Processing Letters 25.2 (2017): 278-282. https://doi.org/10.1109/LSP.2017.2782363
  28. Luo, Yingmin, et al. "Anti-forensics of JPEG compression using generative adversarial networks." 2018 26th European Signal Processing Conference (EUSIPCO). IEEE, 2018.
  29. Zhao, Xinwei, Chen Chen, and Matthew C. Stamm. "A Transferable anti-forensic attack on forensic CNNs using a generative adversarial network." arXiv preprint arXiv:2101.09568 (2021).