Detecting Tampered Videos with Multimedia Forensics and Deep Learning
User-Generated Content (UGC) has become an integral part of the news reporting cycle. As a result, the need to verify videos collected from social media and Web sources is becoming increasingly important for news organisations. While video verification is attracting a lot of attention, there has been limited effort so far in applying video forensics to real-world data. In this work we present an approach for automatic video manipulation detection inspired by manual verification approaches. In a typical manual verification setting, video filter outputs are visually interpreted by human experts. We use two such forensics filters designed for manual verification, one based on Discrete Cosine Transform (DCT) coefficients and a second based on video requantization errors, and combine them with Deep Convolutional Neural Networks (CNN) designed for image classification. We compare the performance of the proposed approach to other works from the state of the art, and discover that, while competing approaches perform better when trained with videos from the same dataset, one of the proposed filters demonstrates superior performance in cross-dataset settings. We discuss the implications of our work and the limitations of the current experimental setup, and propose directions for future research in this area.
KeywordsVideo forensics Video tampering detection Video verification Video manipulation detection User-generated video
This work is supported by the InVID project, which is funded by the European Commission’s Horizon 2020 program under contract number 687786.
- 2.D’Amiano, L., Cozzolino, D., Poggi, G., Verdoliva, L.: Video forgery detection and localization based on 3D patchmatch. In: IEEE International Conference on Multimedia Expo Workshop (ICMEW) (2015)Google Scholar
- 5.He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
- 6.Labartino, D., Bianchi, T., Rosa, A.D., Fontani, M., Vazquez-Padin, D., Piva, A.: Localization of forgeries in MPEG-2 video through GOP size and DQ analysis. In: IEEE International Workshop on Multimedia and Signal Processing, pp. 494–499 (2013)Google Scholar
- 9.Pandey, R., Singh, S., Shukla, K.: Passive copy-move forgery detection in videos. In: IEEE International Conference on Computer and Communications and Technology (ICCCT), pp. 301–306 (2014)Google Scholar
- 10.Papadopoulou, O., Zampoglou, M., Papadopoulos, S., Kompatsiaris, Y., Teyssou, D.: Invid Fake Video Corpus v2.0 (Version 2.0). Dataset on Zenodo (2018)Google Scholar
- 11.Pittaras, N., Markatopoulou, F., Mezaris, V., Patras, I.: Comparison of fine-tuning and extension strategies for deep convolutional neural networks. In: Amsaleg, L., Guðmundsson, G.Þ., Gurrin, C., Jónsson, B.Þ., Satoh, S. (eds.) MMM 2017. LNCS, vol. 10132, pp. 102–114. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-51811-4_9CrossRefGoogle Scholar
- 12.Piva, A.: An overview on image forensics. ISRN Sig. Process. 2013, 22 p. (2013). Article ID 496701Google Scholar
- 13.Rössler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nießner, M.: FaceForensics: a large-scale video dataset for forgery detection in human faces. arXiv preprint arXiv:1803.09179 (2018)
- 16.Su, Y., Xu, J.: Detection of double compression in MPEG-2 videos. In: IEEE 2nd International Workshop on Intelligent Systems and Application (ISA) (2010)Google Scholar
- 17.Subramanyam, A., Emmanuel, S.: Video forgery detection using HOG features and compression properties. In: IEEE 14th International Workshop on Multimedia and Signal Processing (MMSP), pp. 89–94 (2012)Google Scholar
- 18.Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)Google Scholar
- 20.Wu, Y., Jiang, X., Sun, T., Wang, W.: Exposing video inter-frame forgery based on velocity field consistency. In: ICASSP (2014)Google Scholar