Harnessing Machine Learning for Discerning AI-Generated Synthetic Images (2401.07358v2)
Abstract: In the realm of digital media, the advent of AI-generated synthetic images has introduced significant challenges in distinguishing between real and fabricated visual content. These images, often indistinguishable from authentic ones, pose a threat to the credibility of digital media, with potential implications for disinformation and fraud. Our research addresses this challenge by employing machine learning techniques to discern between AI-generated and genuine images. Central to our approach is the CIFAKE dataset, a comprehensive collection of images labeled as "Real" and "Fake". We refine and adapt advanced deep learning architectures like ResNet, VGGNet, and DenseNet, utilizing transfer learning to enhance their precision in identifying synthetic images. We also compare these with a baseline model comprising a vanilla Support Vector Machine (SVM) and a custom Convolutional Neural Network (CNN). The experimental results were significant, demonstrating that our optimized deep learning models outperform traditional methods, with DenseNet achieving an accuracy of 97.74%. Our application study contributes by applying and optimizing these advanced models for synthetic image detection, conducting a comparative analysis using various metrics, and demonstrating their superior capability in identifying AI-generated images over traditional machine learning techniques. This research not only advances the field of digital media integrity but also sets a foundation for future explorations into the ethical and technical dimensions of AI-generated content in digital media.
- J. J. Bird and A. Lotfi, “Cifake: Image classification and explainable identification of ai-generated synthetic images,” 2023.
- Y. Tahk, S. Hong, D.-H. Hong, H. Lee, and T. Lee, “Transition noise characteristics of pmr media with the synthetic antiferromagnetic coupled soft underlayer,” IEEE Transactions on Magnetics, vol. 40, no. 4, pp. 2564–2566, 2004.
- M. Tanaka and H. Kiya, “Fake-image detection with robust hashing,” in 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech), 2021, pp. 40–43.
- S. Selva Birunda, P. Nagaraj, S. Krishna Narayanan, K. Muthamil Sudar, V. Muneeswaran, and R. Ramana, “Fake image detection in twitter using flood fill algorithm and deep neural networks,” in 2022 12th International Conference on Cloud Computing, Data Science & Engineering (Confluence), 2022, pp. 285–290.
- K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2015.
- G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” 2018.
- K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2015.
- M. Hearst, S. Dumais, E. Osuna, J. Platt, and B. Scholkopf, “Support vector machines,” IEEE Intelligent Systems and their Applications, vol. 13, no. 4, pp. 18–28, 1998.
- K. O’Shea and R. Nash, “An introduction to convolutional neural networks,” 2015.
- G. E. Bartos and S. Akyol, “Deep learning for image authentication: A comparative study on real and ai-generated image classification.”
- S. Bhinge and P. Nagpal, “Quantifying the performance gap between real and ai-generated synthetic images in computer vision,” Available at SSRN 4594547.
- V. Vora, J. Savla, D. Mehta, A. Gawade, and R. Mangrulkar, “Classification of diverse ai generated content: An in-depth exploration using machine learning and knowledge graphs,” 2023.
- S. Hinterstoisser, V. Lepetit, P. Wohlhart, and K. Konolige, “On pre-trained image features and synthetic images for deep learning,” in Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0–0.
- D. Meagher, “Efficient synthetic image generation of arbitrary 3-d objects,” in Proceeding of the IEEE Conference on Pattern Recognition and Image Processing, vol. 473, 1982.
- Yuyang Wang (111 papers)
- Yizhi Hao (1 paper)
- Amando Xu Cong (1 paper)