Abstract
The emerging usage of multimedia devices led to a burst in criminal cases where digital forensics investigations are needed. This necessitate development of accurate digital forensic techniques which require not only the confirmation of the data integrity but also the verification of its origin source. To this end, machine and/or deep learning techniques are widely being employed within forensics tools. Nevertheless, while these techniques became an efficient tool for the forensic investigators, they also provided the attackers with novel methods for the data and source falsification. In this paper, we propose a simple and effective anti-forensics attack that uses generative adversarial networks (GANs) to compromise the video’s camera source traces. In our approach, we adopt the popular image-to-image translation GANs to fool the existing algorithms for video source camera identification. Our experimental results demonstrate that the proposed attack can be implemented to successfully compromise the existing forensic methods with 100% probability for non-flat videos while producing the high quality content. The results indicate the need for attack-prone video source camera identification forensics approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Auto-painter: cartoon image generation from sketch by using conditional Wasserstein generative adversarial networks. Neurocomputing 311, 78–87 (2018). https://doi.org/10.1016/j.neucom.2018.05.045
GANs for medical image analysis. Artif. Intell. Med. 109, 101938 (2020). https://doi.org/10.1016/j.artmed.2020.101938
Super-resolution using GANs for medical imaging. Proc. Comput. Sci. 173, 28–35 (2020). https://doi.org/10.1016/j.procs.2020.06.005. International Conference on Smart Sustainable Intelligent Computing and Applications Under ICITETM 2020
Aldausari, N., Sowmya, A., Marcus, N., Mohammadi, G.: Video generative adversarial networks: a review. ACM Comput. Surv. 55(2), 1–25 (2022)
Barni, M., Chen, Z., Tondi, B.: Adversary-aware, data-driven detection of double JPEG compression: how to make counter-forensics harder. In: 2016 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1–6 (2016). https://doi.org/10.1109/WIFS.2016.7823902
Chen, C., Stamm, M.: Robust camera model identification using demosaicing residual features. Multimed. Tools Appl. 80, 1–29 (2021). https://doi.org/10.1007/s11042-020-09011-4
Chen, C., Zhao, X., Stamm, M.C.: MISLGAN: an anti-forensic camera model falsification framework using a generative adversarial network. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 535–539 (2018). https://doi.org/10.1109/ICIP.2018.8451503
Chen, C., Zhao, X., Stamm, M.C.: Generative adversarial attacks against deep-learning-based camera model identification. IEEE Trans. Inf. Forensics Secur. PP, 1 (2019). https://doi.org/10.1109/TIFS.2019.2945198
Cozzolino, D., Thies, J., Rössler, A., Nießner, M., Verdoliva, L.: SpoC: spoofing camera fingerprints (2019)
Cozzolino, D., Verdoliva, L.: Multimedia forensics before the deep learning era. In: Rathgeb, C., Tolosana, R., Vera-Rodriguez, R., Busch, C. (eds.) Handbook of Digital Face Manipulation and Detection. ACVPR, pp. 45–67. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-87664-7_3
Dal Cortivo, D., Mandelli, S., Bestagini, P., Tubaro, S.: CNN-based multi-modal camera model identification on video sequences. J. Imag. 7(8), 135 (2021)
Damiani, J.: A voice deepfake was used to scam a CEO out of \$243,000 (2019). https://www.forbes.com/sites/jessedamiani/2019/09/03/a-voice-deepfake-was-used-to-scam-a-ceo-out-of-243000/?sh=34e8298a2241
Das, T.K.: Anti-forensics of JPEG compression detection schemes using approximation of DCT coefficients. Multimed. Tools Appl. 77(24), 31835–31854 (2018)
Duan, B., Wang, W., Tang, H., Latapie, H., Yan, Y.: Cascade attention guided residue learning GAN for cross-modal translation (2019)
Flor, E., Aygun, R., Mercan, S., Akkaya, K.: PRNU-based source camera identification for multimedia forensics. In: 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science (IRI), pp. 168–175 (2021). https://doi.org/10.1109/IRI51335.2021.00029
Gauthier, J.: Conditional generative adversarial nets for convolutional face generation (2015)
Goodfellow, I., et al.: Generative adversarial nets. Advances in Neural Information Processing Systems, vol. 27 (2014)
Hosler, B., et al.: A video camera model identification system using deep learning and fusion. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8271–8275 (2019). https://doi.org/10.1109/ICASSP.2019.8682608
Jeong, S., Lee, J., Sohn, K.: Multi-domain unsupervised image-to-image translation with appearance adaptive convolution (2022)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation (2017)
Kirchner, M., Bohme, R.: Hiding traces of resampling in digital images. IEEE Trans. Inf. Forensics Secur. 3(4), 582–592 (2008)
Korshunova, I., Shi, W., Dambre, J., Theis, L.: Fast face-swap using convolutional neural networks (2016)
Li, Y., Min, M.R., Shen, D., Carlson, D., Carin, L.: Video generation from text. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, AAAI 2018/IAAI 2018/EAAI 2018. AAAI Press (2018)
Mayer, O., Stamm, M.C.: Countering anti-forensics of lateral chromatic aberration. Association for Computing Machinery, New York, NY, USA (2017)
Peng, F., Yin, L., Long, M.: BDC-GAN: bidirectional conversion between computer-generated and natural facial images for anti-forensics. IEEE Trans. Circ. Syst. Video Technol. 32, 1 (2022). https://doi.org/10.1109/TCSVT.2022.3177238
Rong, D., Wang, Y., Sun, Q.: Video source forensics for IoT devices based on convolutional neural networks. Open J. Internet Things (OJIOT) 7(1), 23–31 (2021)
Sharma, S., Ravi, H., Subramanyam, A., Emmanuel, S.: Anti-forensics of median filtering and contrast enhancement. J. Vis. Commun. Image Represent. 66(C), 102682 (2020)
Shullani, D., Fontani, M., Iuliani, M., Alshaya, O., Piva, A.: Vision: a video and image dataset for source identification. EURASIP J. Inf. Secur. 2017, 15 (2017). https://doi.org/10.1186/s13635-017-0067-2
Stamm, M.C., Lin, W.S., Liu, K.J.R.: Temporal forensics and anti-forensics for motion compensated video. IEEE Trans. Inf. Forensics Secur. 7(4), 1315–1329 (2012). https://doi.org/10.1109/TIFS.2012.2205568
Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., Nießner, M.: Face2Face: real-time face capture and reenactment of RGB videos, vol. 62, no. 1 (2018)
Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation (2017)
Veksler, M., Aygun, R., Akkaya, K., Iyengar, S.: Video origin camera identification using ensemble CNNs of positional patches. In: 2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR) (2022). (in Press)
Venkatesh, S., Zhang, H., Ramachandra, R., Raja, K., Damer, N., Busch, C.: Can GAN generated morphs threaten face recognition systems equally as landmark based morphs? - vulnerability and detection (2020)
Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction. ArXiv abs/1706.08033 (2017)
Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NIPS 2016, pp. 613–621. Curran Associates Inc., Red Hook, NY, USA (2016)
Yu, J., Xue, H., Liu, B., Wang, Y., Zhu, S., Ding, M.: GAN-based differential private image privacy protection framework for the internet of multimedia things. Sensors 21(1), 58 (2021)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2242–2251 (2017). https://doi.org/10.1109/ICCV.2017.244
Zou, H., Yang, P., Ni, R., Zhao, Y., Zhou, N.: Anti-forensics of image contrast enhancement based on generative adversarial network (2021)
Acknowledgements
Research was sponsored by the Army Research Office and was accomplished under Grant Number W911NF-21-1-0264. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Office or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Veksler, M., Caspard, C., Akkaya, K. (2023). Image-to-Image Translation Generative Adversarial Networks for Video Source Camera Falsification. In: Goel, S., Gladyshev, P., Nikolay, A., Markowsky, G., Johnson, D. (eds) Digital Forensics and Cyber Crime. ICDF2C 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 508. Springer, Cham. https://doi.org/10.1007/978-3-031-36574-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-36574-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36573-7
Online ISBN: 978-3-031-36574-4
eBook Packages: Computer ScienceComputer Science (R0)