A Dual-Domain Face Forgery and Deepfake Detection Framework

Authors

• Neha Pradyumna Bora, Assistant Professor, Department of Computer Engineering, SNJB’s Late Sau. Kantabai Bhavarlalji Jain College of Engineering, Chandwad, Dist. Nashik, Maharashtra, IndiaFollow
• Pradyumna Mulchand Bora, Assistant Professor, Department of Mechanical Engineering, SNJB’s Late Sau. Kantabai Bhavarlalji Jain College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India
• Rushikesh Sanjay Kumavat, Department of Computer Engineering, SNJB’s Late Sau. Kantabai Bhavarlalji Jain College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India
• Raunak Manoj Gangwal, Department of Computer Engineering, SNJB’s Late Sau. Kantabai Bhavarlalji Jain College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India
• Prit Sandesh Jain, Department of Computer Engineering, SNJB’s Late Sau. Kantabai Bhavarlalji Jain College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India
• Hardik Vijay Ostwal, Department of Computer Engineering, SNJB’s Late Sau. Kantabai Bhavarlalji Jain College of Engineering, Chandwad, Dist. Nashik, Maharashtra, India

Corresponding Author

Neha Pradyumna Bora

Subject Area

Computer Science

Article Type

Original Study

Abstract

Concerns about media authenticity, privacy, and information security arising from rapid advances in deepfake technology have made it increasingly important to detect manipulated facial content reliably. The primary goal of our work was to develop a deepfake detection model with high generalization across multiple datasets. To achieve this, we developed a hybrid detection approach that combines spatial visual texture analysis and frequency-domain analysis to detect manipulated facial images. Our approach includes convolutional spatial feature extraction from facial images and frequency—domain representations of the same images obtained by applying the fast Fourier transform. To help alleviate concerns about overreliance on frequency—domain cues, we have introduced a gated fusion strategy that allows balanced contributions from both spatial and frequency—domain features. In addition, a multiphase training strategy was used during model development, with the frequency—domain branch incorporated in phases using a freeze—unfreeze optimization approach. The trained model was evaluated using separate test datasets of previously unseen facial imagery with minimal additional fine-tuning. Results show strong precision in detecting manipulated images on the same dataset used for training, as well as improved generalization across unseen datasets, particularly when the test dataset contains few examples of the same manipulation. These findings suggest that controlling feature integration and model training dynamics improves the stability of deepfake detection across diverse manipulation scenarios.

Keywords

Cross-dataset robustness, Deepfake detection, Digital media integrity, Multimodal feature fusion, Spectral representation learning, Training strategy regulation

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.

Recommended Citation

Bora, Neha Pradyumna; Bora, Pradyumna Mulchand; Kumavat, Rushikesh Sanjay; Gangwal, Raunak Manoj; Jain, Prit Sandesh; and Ostwal, Hardik Vijay (2026) "A Dual-Domain Face Forgery and Deepfake Detection Framework," Mansoura Engineering Journal: Vol. 51 : Iss. 3 , Article 11.
Available at: https://doi.org/10.58491/2735-4202.3449