Fake Images Identification on Social Media Application Via Generated Adversarial Networks and DenseNet
Keywords:
Fake Images detection, Generative Adversarial Networks (GAN), Deep Learning (GAN-CNN)Abstract
The rapid spread of fake images on social media has become a major concern for individuals, organizations, and governments. These images are often generated using advanced techniques, such as Generative Adversarial Networks (GANs), to manipulate public opinion and spread misinformation. Given the high visual quality of GAN-generated fake faces, detecting them has become increasingly challenging. If misused for image tampering, these synthetic images could lead to serious ethical, moral, and legal issues. Therefore, developing automated detection tools is essential to identify and mitigate the risks associated with synthetic media. In this study, we introduce a DenseNet based approach to detect GAN-generated fake images. Experimental results demonstrate that our proposed model achieves high accuracy, exceeding 98.1%, in distinguishing real and fake faces. Also, it acquired high Sensitivity of 1.00%, Specificity of 97. 6% and F1 scores of 98.6%.
References
Raturi, Rohit. "Machine learning implementation for identifying fake accounts in social network." International Journal of Pure and Applied Mathematics 118.20 (2018): 4785-4797.
Schmidhuber, Jurgen. "Multi-column deep neural networks for image classification." Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2012.
Goodfellow, Ian, et al. "Generative adversarial nets." Advances in neural information processing systems 27 (2014).
Dumoulin, Vincent, Jonathon Shlens, and Manjunath Kudlur. "A learned representation for artistic style." arXiv preprint arXiv:1610.07629 (2016).
Aggarwal, Alankrita, Mamta Mittal, and Gopi Battineni. "Generative adversarial network: An overview of theory and applications." International Journal of Information Management Data Insights 1.1 (2021): 100004.
Cong, Yulai, et al. "Gan memory with no forgetting." Advances in Neural Information Processing Systems 33 (2020): 16481-16494.
Marra, Francesco, et al. "Detection of gan-generated fake images over social networks." 2018 IEEE conference on multimedia information processing and retrieval (MIPR). IEEE, 2018.
Frank, Joel, et al. "Leveraging frequency analysis for deep fake image recognition." International conference on machine learning. PMLR, 2020.
McCloskey, Scott, and Michael Albright. "Detecting gan-generated imagery using color cues." arXiv preprint arXiv:1812.08247 (2018).
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.
Choi, Hak-Yeol, et al. "Detecting composite image manipulation based on deep neural networks." 2017 international conference on systems, signals and image processing (IWSSIP). IEEE, 2017.
Li, Chuqiao, et al. "A continual deepfake detection benchmark: Dataset, methods, and essentials." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2023.
Jaiswal, Ankit Kumar, and Rajeev Srivastava. "A technique for image splicing detection using hybrid feature set." Multimedia Tools and Applications 79.17 (2020): 11837-11860.
Karras, Tero, et al. "Progressive growing of gans for improved quality, stability, and variation. arXiv 2017." arXiv preprint arXiv:1710.10196 (2018): 1-26.
Campos, Gabriel Fillipe Centini, et al. "Machine learning hyperparameter selection for contrast limited adaptive histogram Equalization." EURASIP Journal on Image and Video Processing 2019.1 (2019): 1-18. doi.org/10.1186/s13640-019-0445-4
Huang, Gao, et al. "Densely connected convolutional networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
Afchar, Darius, et al. "Mesonet: a compact facial video forgery detection network." 2018 IEEE international workshop on information forensics and security (WIFS). IEEE, 2018.
Mo, Huaxiao, Bolin Chen, and Weiqi Luo. "Fake faces identification via convolutional neural network." Proceedings of the 6th ACM workshop on information hiding and multimedia security. 2018.
Wang, Yaqing, et al. "Eann: Event adversarial neural networks for multi-modal fake news detection." Proceedings of the 24th acm sigkdd international conference on knowledge discovery & data mining. 2018.
Singhal, Shivangi, et al. "Spotfake: A multi-modal framework for fake news detection." 2019 IEEE fifth international conference on multimedia big data (BigMM). IEEE, 2019.
