Deepfake Detection Using Multimodal Biometric Fusion

The rapid advancement in using AI techniques for creating realistic synthetic media, commonly known as deepfakes, possess the risks of misinformation, identity fraud, and social manipulation. This paper systematically reviews the repercussions of deepfakes and addresses these critical issues through an innovative multimodal approach that integrates multiple biometric traits, unlike unimodal detection, which faces bottlenecks due to its vulnerability to spoofing. To achieve a combined analysis, this model integrates visual features, auditory features, and behavioral features. This also compares various datasets used and fusion strategies. Detecting deepfakes using a multimodal approach isn’t easy and gives rise to challenges such as complexity in fusion, limited datasets, and high computing power. This study serves as a foundation for future advancements and can be expanded to be part of apps, social media tools, digital forensics and even help in governance, making it more reliable.

CyberSecurity, DeepFake, DeepFake Detection, Feature Extraction, Fusion Strategies, Multimodal Biometric Fusion.

1. Multimodal Deepfake Detection,Authors: Prof. Sneha G, Prof. Divya S, Lavanya R, Leesha V Kumar, Navyatha A, Nishu Agarwal. Available:https://doi.org/10.22214/ijraset.2024.62936 [Google Scholar] [Crossref]

2. A Research on Deepfake Face Detection Techniques Based on Multimodal Biometric Cross – Verification, Haozhe Wu, School of Computer and Software, Hohai University, Nanjing, Jiangsu, China, ITM Web of Conferences 78, 02017 (2025),CSEIT 2025 Available:https://doi.org/10.1051/itmconf/20257802017 [Google Scholar] [Crossref]

3. Robust Approach to Multimodal Deepfake Detection, Salvi, D.; Liu, H.; Mandelli,S.; Bestagini, P.; Zhou, W.; Zhang, W.;Tubaro, S. A J.Imaging 2023. Available : https://doi.org/10.3390/jimaging9060122 [Google Scholar] [Crossref]

4. From Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challenges, Authors: Ping Liu, Senior Member, IEEE, Qiqi Tao, and Joey Tianyi Zhou, Senior Member, IEEE. Available: https://arxiv.org/abs/2406.06965 [Google Scholar] [Crossref]

5. A Multimodal Framework for DeepFake Detection, Authors: Kashish Gandhi, Prutha Kulkarni, Taran Shah, Piyush Chaudhari, Meera Narvekar and Kranti Ghag Available : https://arxiv.org/abs/2410.03487 [Google Scholar] [Crossref]

6. Deepfake Detection: A Multi-Algorithmic and Multi-Modal Approach for Robust Detection and Analysis, Authors: Sagar Nailwal,Nongmeikapam Thoiba Singh,Arbaz Raza,Saksham Singhal. Available:https://ieeexplore.ieee.org/abstract/document/10369155/ [Google Scholar] [Crossref]

7. How Multimodal Biometric Systems are Winning the War on AI-Generated Deepfakes? Author: Arjun Singh. Available : https://blog.mantratec.com/Multimodal-Biometric-Systems-Vs-AI-Deepfakes [Google Scholar] [Crossref]

8. Rui Wang, Dengpan Ye, Long Tang, Yunming Zhang, Jiacheng Deng (2024) AVT2-DWF: Improving Deepfake Detection with Audio-Visual Fusion and Dynamic Weighting Strategies. Available : https://arxiv.org/abs/2403.14974⁠ [Google Scholar] [Crossref]

9. Zhimao Lai, Yufei Wang, Renhai Feng, Xianglei Hu, Haifeng Xu (2022) Multi-Feature Fusion Based Deepfake Face Forgery Video Detection. Available :https://www.mdpi.com/2079-8954/10/2/31⁠ [Google Scholar] [Crossref]

10. Siddiqui Muhammad Yasir, Hyun Kim (2025), Lightweight Deepfake Detection Based on Multi-Feature Fusion. Available : https://doi.org/10.3390/app15041954⁠ [Google Scholar] [Crossref]

11. Yuncan Sheng, Zhengrui Zou, Zongxuan Yu, Wei Ou (2025), ID-Insensitive Deepfake Detection Model Based on Multi-Attention Mechanism. Available : https://www.nature.com/articles/s41598-025-96254-6 [Google Scholar] [Crossref]

12. Hasam Khalid, Shahroz Tariq, Minha Kim, Simon S. Woo (2021) FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset. Available:https://github.com/DASHLab/FakeAVCeleb⁠ [Google Scholar] [Crossref]

13. Junke Wang, Zuxuan Wu, Wenhao Ouyang, Xintong Han, Jingjing Chen, Ser-Nam Lim, YuGang Jiang (2021) M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection. Available : https://arxiv.org/abs/2104.09770⁠ [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition