Did You Note My Palette? Unveiling Synthetic Images Through Color Statistics
Authors: 
Lea Uhlenbrock, Davide Cozzolino, Denise Moussa, Luisa Verdoliva, Christian RiessAuthors Info & Claims
Lea Uhlenbrock, Davide Cozzolino, Denise Moussa, Luisa Verdoliva, Christian RiessAuthors Info & ClaimsPages 47 - 52
Abstract
High-quality artificially generated images are widely available now and increasingly realistic, posing challenges for image forensics in distinguishing them from real ones. Unfortunately, building a single detector that generalizes well to unseen generators is very difficult, creating the need for diverse cues. In this paper, we show that natural and synthetic images differ in their color statistics, possibly due to the widely used perceptual loss, which is more sensitive to brightness than to chroma differences. Consequently, color statistics offer valuable cues for forensic analysis and the development of robust detectors. Our experiments using simple hand-crafted color functions with a random forest achieve 91% accuracy averaged over all tested Diffusion Models, even with limited training samples.
References
[1]
Adobe. 2024. Firefly. https://www.adobe.com/sensei/generative-ai/firefly.html.
[2]
M.A. Amin, Y. Hu, H. She, J. Li, Y. Guan, and M.Z. Amin. 2023. Exposing Deepfake Frames through Spectral Analysis of Color Channels in Frequency Domain. In International Workshop on Biometrics and Forensics. IEEE, 1--6.
[3]
M. Barni, K. Kallas, E. Nowroozi, and B. Tondi. 2020. CNN Detection of GAN-Generated Face Images Based on Cross-Band Co-Occurrences Analysis. In IEEE International Workshop on Information Forensics and Security). IEEE, 1--6.
[4]
N. Bonettini, P. Bestagini, S. Milani, and S. Tubaro. 2021. On the Use of Benford's Law to Detect GAN-Generated Images. In International Conference on Pattern Recognition. IEEE, 5495--5502.
[5]
J. Bruna, P. Sprechmann, and Y. LeCun. 2016. Super-Resolution with Deep Convolutional Sufficient Statistics.
[6]
B. Chen, X. Liu, Y. Zheng, G. Zhao, and Y.-Q. Shi. 2021. A Robust GAN-Generated Face Detection Method Based on Dual-Color Spaces and an Improved Xception. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 32, 6 (2021), 3527--3538.
[7]
R. Corvi, D. Cozzolino, G. Poggi, K. Nagano, and L. Verdoliva. 2023 a. Intriguing Properties of Synthetic Images: From Generative Adversarial Networks to Diffusion Models. In IEEE Conference on Computer Vision and Pattern Recognition. 973--982.
[8]
R. Corvi, D. Cozzolino, G. Zingarini, G. Poggi, K. Nagano, and L. Verdoliva. 2023 b. On the Detection of Synthetic Images Generated by Diffusion Models. In International Conference on Acoustics, Speech and Signal Processing. IEEE, 1--5.
[9]
D.-T. Dang-Nguyen, C. Pasquini, V. Conotter, and G. Boato. 2015. RAISE: A Raw Images Dataset for Digital Image Forensics. In ACM Multimedia Systems Conference. 219--224.
[10]
A. Dosovitskiy and T. Brox. 2016. Generating Images with Perceptual Similarity Metrics Based on Deep Networks. In Advances in Neural Information Processing Systems, Vol. 29.
[11]
H. Farid. 2022a. Lighting (In)consistency of Paint by Text. Technical Report 2207.13744. arXiv.
[12]
H. Farid. 2022b. Perspective (In)consistency of Paint by Text. Technical Report 2206.14617. arXiv.
[13]
J. Fridrich and J. Kodovsky. 2012. Rich Models for Steganalysis of Digital Images. IEEE Transactions on Information Forensics and Security, Vol. 7, 3 (2012), 868--882.
[14]
M. Goebel, L. Nataraj, T. Nanjundaswamy, T. Manhar Mohammed, S. Chandrasekaran, and B.S. Manjunath. 2020. Detection, Attribution and Localization of GAN Generated Images.
[15]
D. Gragnaniello, D. Cozzolino, F. Marra, G. Poggi, and L. Verdoliva. 2021. Are GAN Generated Images Easy to Detect? A Critical Analysis of the State-of-the-Art. In IEEE International Conference on Multimedia and Expo. IEEE, 1--6.
[16]
P. He, H. Li, and H. Wang. 2019. Detection of Fake Images via the Ensemble of Deep Representations from Multi Color Spaces. In IEEE International Conference on Image Processing. IEEE, 2299--2303.
[17]
J. Ho, A. Jain, and P. Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems, Vol. 33. 6840--6851.
[18]
Midjourney Inc. 2024. Midjourney. https://www.midjourney.com/home.
[19]
J. Johnson, A. Alahi, and L. Fei-Fei. 2016. Perceptual Losses for Real-Time Style Transfer and Super-Resolution. In European Conference on Computer Vision. Springer, 694--711.
[20]
E.-G. Lee, I. Lee, and S.-B. Yoo. 2023. ClueCatcher: Catching Domain-Wise Independent Clues for Deepfake Detection. Mathematics, Vol. 11, 18 (2023), 3952.
[21]
H. Li, B. Li, S. Tan, and J. Huang. 2020. Identification of Deep Network Generated Images Using Disparities in Color Components. Signal Processing, Vol. 174 (2020), 107616.
[22]
T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C.L. Zitnick. 2014. Microsoft COCO: Common Objects in Context. In European Conference on Computer Vision. Springer, 740--755.
[23]
B. Liu, F. Yang, X. Bi, B. Xiao, W. Li, and X. Gao. 2022. Detecting Generated Images by Real Images. In European Conference on Computer Vision. Springer, 95--110.
[24]
S. Mandelli, N. Bonettini, P. Bestagini, and S. Tubaro. 2022. Detecting GAN-Generated Images by Orthogonal Training of Multiple CNNs. In IEEE International Conference on Image Processing. IEEE, 3091--3095.
[25]
F. Marra, D. Gragnaniello, L. Verdoliva, and G. Poggi. 2018. Do GANs Leave Artificial Fingerprints?. In IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). 506--511.
[26]
F. Matern, C. Riess, and M. Stamminger. 2019. Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations. In IEEE Winter Applications of Computer Vision Workshops. IEEE, 83--92.
[27]
S. McCloskey and M. Albright. 2019. Detecting GAN-Generated Imagery Using Saturation Cues. In EEE International Conference on Image Processing. IEEE, 4584--4588.
[28]
S. Mo, P. Lu, and X. Liu. 2022. AI-Generated Face Image Identification with Different Color Space Channel Combinations. Sensors, Vol. 22, 21 (2022), 8228.
[29]
U. Ojha, Y. Li, and Y.J. Lee. 2023. Towards Universal Fake Image Detectors that Generalize Across Generative Models. In IEEE Conference on Computer Vision and Pattern Recognition. 24480--24489.
[30]
OpenAI. 2024. DALL-E 3. https://openai.com/dall-e-3.
[31]
T. Qiao, Y. Chen, X. Zhou, R. Shi, H. Shao, K. Shen, and X. Luo. 2023. CSC-Net: Cross-Color Spatial Co-occurrence Matrix Network for Detecting Synthesized Fake Images. IEEE Transactions on Cognitive and Developmental Systems (2023).
[32]
R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10684--10695.
[33]
R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer. 2024. Stable Diffusion. https://github.com/CompVis/stable-diffusion.
[34]
C. Schuhmann, R. Vencu, R. Beaumont, R. Kaczmarczyk, C. Mullis, A. Katta, T. Coombes, J. Jitsev, and A. Komatsuzaki. 2021. Laion-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.
[35]
C. Tan, Y. Zhao, S. Wei, G. Gu, and Y. Wei. 2023. Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection. In IEEE Conference on Computer Vision and Pattern Recognition. 12105--12114.
[36]
European Union. 2021. Artificial Intelligence Act, Article 10, paragraph 3. https://artificialintelligenceact.eu/the-act/.
[37]
S.-Y. Wang, O. Wang, R. Zhang, A. Owens, and A.A. Efros. 2020. CNN-Generated Images Are Surprisingly Easy to Spot... for Now. In IEEE Conference on Computer Vision and Pattern Recognition. 8695--8704.
[38]
Z. Wang, J. Bao, W. Zhou, W. Wang, H. Hu, H. Chen, and H. Li. 2023. DIRE for Diffusion-Generated Image Detection.
[39]
K. Zeng, X. Yu, B. Liu, Y. Guan, and Y. Hu. 2023. Detecting Deepfakes in Alternative Color Spaces to Withstand Unseen Corruptions. In International Workshop on Biometrics and Forensics. IEEE, 1--6.
[40]
K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang. 2017. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing, Vol. 26, 7 (2017), 3142--3155.
[41]
L. Zhang, Y. Zhou, C. Barnes, S. Amirghodsi, Z. Lin, E. Shechtman, and J. Shi. 2022. Perceptual Artifacts Localization for Inpainting. In European Conference on Computer Vision. Springer, 146--164.
[42]
R. Zhang, P. Isola, A. A Efros, E. Shechtman, and O. Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In IEEE Conference on Computer Vision and Pattern Recognition. 586--595.
[43]
Xu Zhang, Svebor Karaman, and Shih-Fu Chang. 2019. Detecting and Simulating Artifacts in GAN Fake Images. In IEEE International Workshop on Information Forensics and Security. io
Index Terms
- Did You Note My Palette? Unveiling Synthetic Images Through Color Statistics
Recommendations
Using assorted color spaces and pixel window sizes for colorization of grayscale images
ICWET '10: Proceedings of the International Conference and Workshop on Emerging Trends in TechnologyThere is no exact solution for colorization of grayscale images. In the initial work done [23], color traits transfer techniques to color grayscale images are proposed. The main focus of the techniques [23] is to minimise the human efforts needed in ...
Comparative analysis of the quantization of color spaces on the basis of the CIELAB color-difference formula
This article discusses the CIELAB color spave within the limits of optimal colors including the complete volume of object colors. A graphical representation of this color space is composed of planes of constant lightness L* with an net of lines parallel ...
Color image histogram equalization by absolute discounting back-off
A novel color image histogram equalization approach is proposed that exploits the correlation between color components and it is enhanced by a multi-level smoothing technique borrowed from statistical language engineering. Multi-level smoothing aims at ...
Comments
Information & Contributors
Information
Published In
June 2024
305 pages
ISBN:9798400706370
DOI:10.1145/3658664
- General Chair:
- Fernando Pérez-González,
- Program Chairs:
- Pedro Comesaña-Alfaro,
- Christian Krätzer,
- Hong Vicky Zhao
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 24 June 2024
Check for updates
Badges
Best Paper
Author Tags
Qualifiers
- Short-paper
Funding Sources
- Research and Training Group 2475 Cybercrime and Forensic Computing (grant number 393541319/GRK2475/2-2024)
Conference
IH&MMSEC '24
Sponsor:
IH&MMSEC '24: ACM Workshop on Information Hiding and Multimedia Security
June 24 - 26, 2024
Baiona, Spain
Acceptance Rates
Overall Acceptance Rate 128 of 318 submissions, 40%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 159Total Downloads
- Downloads (Last 12 months)159
- Downloads (Last 6 weeks)45
Reflects downloads up to 01 Oct 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in