DeepSpace: Navigating the Frontier of Deepfake Identification Using Attention-Driven Xception and a Task-Specific Subspace

Ayush Roy, Sk Mohiuddin, Maxim Minenko, Dmitrii Kaplun, Dmitrii Kaplun, Ram Sarkar

2025

Abstract

The recent advancements in deepfake technology pose significant challenges in detecting manipulated media content and preventing its malicious use in different areas. Using ConvNets feature spaces and fine-tuning them for deepfake classification can lead to unwanted modifications and artifacts in the feature space. To address this, we propose a model that uses Xception as the backbone and a Spatial Attention Module (SAM) to leverage spatial information using shallower features like texture, color, and shape, as well as deeper finegrained features. We also create a task-specific subspace for projecting spatially enriched features, which boosts the overall model performance. To do this, we utilize Gram-Smith orthogonalization on the flattened features of real and fake images to produce the basis vectors for our subspace. We evaluate the proposed method using two widely used and standard deepfake video datasets: FaceForensics++ and Celeb-DF (V2). We conduct experiments following two different setups: intra-dataset (trained and tested on the same dataset) and inter-dataset (trained and tested on separate datasets). The performance of the proposed model is comparable to that of state-of-the-art methods, confirming its robustness and generalization ability. The code is made available at https://github.com/AyushRoy2001/DeepSpace.

Paper Citation

in Harvard Style

Roy A., Mohiuddin S., Minenko M., Kaplun D. and Sarkar R. (2025). DeepSpace: Navigating the Frontier of Deepfake Identification Using Attention-Driven Xception and a Task-Specific Subspace. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 163-172. DOI: 10.5220/0013173700003912

in Bibtex Style

@conference{visapp25,
author={Ayush Roy and Sk Mohiuddin and Maxim Minenko and Dmitrii Kaplun and Ram Sarkar},
title={DeepSpace: Navigating the Frontier of Deepfake Identification Using Attention-Driven Xception and a Task-Specific Subspace},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={163-172},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013173700003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - DeepSpace: Navigating the Frontier of Deepfake Identification Using Attention-Driven Xception and a Task-Specific Subspace
SN - 978-989-758-728-3
AU - Roy A.
AU - Mohiuddin S.
AU - Minenko M.
AU - Kaplun D.
AU - Sarkar R.
PY - 2025
SP - 163
EP - 172
DO - 10.5220/0013173700003912
PB - SciTePress