Abstract
The spread of deepfake content has created distrust, misconception, and fraud all around the world. Swapping faces between individuals seamlessly or generating AI-created fake faces has become easier than ever with AI tools like DALL-E, Midjourney, ChatGPT, and Google Gemini. AI generated obscene and malicious content has become progressively prevalent and widely circulated on social media due to the misuse of generative adversarial techniques. To prevent AI generated fake images from causing harm to the identity and social integrity of a person or community, this research presents a deep learning model called ‘DeFakeNet’ based on the advanced ResNet50V2 CNN architecture, designed to detect and classify whether a person’s face is real or fake. While past research has relied extensively on pre-trained models and limited dataset, DeFakeNet was trained on a custom-developed dataset titled ‘Real vs Fake Faces Balanced Dataset with Multiple Dataset Splits’, a mixed dataset comprising 10,000 high quality balanced real and fake face images. Upon testing with unseen data, the proposed model obtained 91.95% test accuracy and an AUC score of 97.64%, setting new records in this field. A critical scrutiny of all the diverse evaluation metrics, ROC and Precision-Recall Curves is presented in this paper, which is rarely discussed thoroughly in previous research. Additionally, the model performance comparison with current methods shows robust real world reliability and application toward the detection of evolving deepfakes.
References
Kim, Eunji, and Sungzoon Cho. "Exposing Fake Faces Through Deep Neural Networks Combining Content and Trace Feature Extractors." IEEe Access 9 (2021): 123493-123503.
Kosarkar, Usha, Gopal Sarkarkar, and Shilpa Gedam. "Revealing and Classification of Deepfakes Video's Images Using a Customize Convolution Neural Network Model." Procedia Computer Science 218 (2023): 2636-2652.
Abu-Ein, Ashraf A., Obaida M. Al-Hazaimeh, Alaa M. Dawood, and Andraws I. Swidan. "Analysis of the Current State of Deepfake Techniques-Creation and Detection Methods." Indonesian Journal of Electrical Engineering and Computer Science 28, no. 3 (2022): 1659-1667.
Ben Aissa, Fatma, Monia Hamdi, Mourad Zaied, and Mahmoud Mejdoub. "An Overview of GAN-DeepFakes Detection: Proposal, Improvement, and Evaluation." Multimedia Tools and Applications 83, no. 11 (2024): 32343-32365.
Krueger, Natalie, Mounika Vanamala, and Rushit Dave. "Recent Advancements in the Field of Deepfake Detection." arXiv preprint arXiv:2308.05563 (2023).
KV, Daya Sagar, D. B. K. Kamesh, T. Srinivasa Rao, and Chinta Venkata Murali Krishna. "Detecting Fake Faces in Smart Cities Security Surveillance Using Image Recognition and Convolutional Neural Networks." ECS Transactions 107, no. 1 (2022): 19749.
Zhang, Mingxu, Hongxia Wang, Peisong He, Asad Malik, and Hanqing Liu. "Improving GAN-Generated Image Detection Generalization Using Unsupervised Domain Adaptation." In 2022 IEEE International Conference on Multimedia and Expo (ICME), IEEE, 2022, 1-6.
Sharma, Jatin, Sahil Sharma, Vijay Kumar, Hany S. Hussein, and Hammam Alshazly. "Deepfakes Classification of Faces Using Convolutional Neural Networks." Traitement du Signal 39, no. 3 (2022).
Wen, Lilong, and Dan Xu. "Face Image Manipulation Detection." In IOP conference series: materials science and engineering, vol. 533, no. 1, IOP Publishing, 2019, 012054.
Dhar, Arpita, Prima Acharjee, Likhan Biswas, Shemonti Ahmed, and Abida Sultana. "Detecting Deepfake Images Using Deep Convolutional Neural Network." PhD diss., Brac University, 2021.
Tolosana, Ruben, Ruben Vera-Rodriguez, Julian Fierrez, Aythami Morales, and Javier Ortega-Garcia. "Deepfakes and Beyond: A Survey of Face Manipulation and Fake Detection." Information Fusion 64 (2020): 131-148.
Goodfellow, Ian, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. "Generative Adversarial Networks." Communications of the ACM 63, no. 11 (2020): 139-144.
Wang, Zhikan, Zhongyao Cheng, Jiajie Xiong, Xun Xu, Tianrui Li, Bharadwaj Veeravalli, and Xulei Yang. "A Timely Survey on Vision Transformer for Deepfake Detection." arXiv preprint arXiv:2405.08463 (2024).
Petmezas, Georgios, Vazgken Vanian, Konstantinos Konstantoudakis, Elena EI Almaloglou, and Dimitris Zarpalas. "Video Deepfake Detection Using A Hybrid CNN-LSTM-Transformer Model for Identity Verification." Multimedia Tools and Applications (2025): 1-20.
Suratkar, Shraddha, and Faruk Kazi. "Deep Fake Video Detection Using Transfer Learning Approach." Arabian Journal for Science and Engineering 48, no. 8 (2023): 9727-9737.
Tunguz, Bojan. “140k Real and Fake Faces.” Kaggle, 2019. https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces
Tunguz, Bojan. “1 Million Fake Faces.” Kaggle, 2020. https://www.kaggle.com/datasets/tunguz/1-million-fake-faces.
Arnaud58. “Flickr-Faces-HQ Dataset (FFHQ).” Kaggle, 2019. https://www.kaggle.com/datasets/arnaud58/flickrfaceshq-dataset-ffhq.
Kunichetty, Sachchit. “Real vs Fake Faces – 10k (RVF10K).” Kaggle, 2023. https://www.kaggle.com/datasets/sachchitkunichetty/rvf10k.
Samal, Debasish, Pooja Agrawal, and Vikas Madaan. “Real vs Fake Faces Balanced Dataset with Multiple Dataset Splits (Version 1.0).” Zenodo, 2024. https://doi.org/10.5281/zenodo.14532968
Pathak, Lakshin, Mili Virani, Mohammad S. Obaidat, Prachita Patel, Jigna J. Hathaliya, Nilesh Kumar Jadav, Sudeep Tanwar, and Nagendar Yamsani. "A Transfer Learning-Based Intelligent Judiciary System for Public Safety." In 2024 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI), IEEE, 2024, 1-6.
He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep Residual Learning for Image Recognition." In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, 770-778.
Huang, Gao, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. "Densely Connected Convolutional Networks." In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, 4700-4708.
Szegedy, Christian, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. "Going Deeper with Convolutions." In Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, 1-9.
Tan, Mingxing, and Quoc Le. "Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks." In International conference on machine learning, PMLR, 2019, 6105-6114.
Dosovitskiy, Alexey. "An Image is Worth 16x16 Words: Transformers for image recognition at scale." arXiv preprint arXiv:2010.11929 (2020).
Kim, Chaewon. "Distinguishing AI-Generated and Real Images Using Swin-Transformer." In 2025 IEEE Integrated STEM Education Conference (ISEC), IEEE, 2025, 1-6.