Deepfake Detection
Deepfake detection research aims to develop robust methods for identifying manipulated media, combating the spread of misinformation and fraudulent content. Current efforts focus on improving the generalization of detection models across diverse deepfake generation techniques, employing architectures like Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs), often incorporating multimodal analysis (audio-visual) and leveraging pre-trained models like CLIP. This field is crucial for maintaining digital media integrity and security, with implications for law enforcement, cybersecurity, and the broader fight against disinformation.
Papers
Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content
Rohit Kundu, Hao Xiong, Vishal Mohanty, Athula Balachandran, Amit K. Roy-Chowdhury
Region-Based Optimization in Continual Learning for Audio Deepfake Detection
Yujie Chen, Jiangyan Yi, Cunhang Fan, Jianhua Tao, Yong Ren, Siding Zeng, Chu Yuan Zhang, Xinrui Yan, Hao Gu, Jun Xue, Chenglong Wang, Zhao Lv, Xiaohui Zhang
Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning
Dragos-Alexandru Boldisor, Stefan Smeu, Dan Oneata, Elisabeta Oneata
Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
Florinel-Alin Croitoru, Andrei-Iulian Hiji, Vlad Hondru, Nicolae Catalin Ristea, Paul Irofti, Marius Popescu, Cristian Rusu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah
Adaptive Meta-Learning for Robust Deepfake Detection: A Multi-Agent Framework to Data Drift and Model Generalization
Dinesh Srivasthav P, Badri Narayan Subudhi
Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights
Ammarah Hashmi, Sahibzada Adil Shahzad, Chia-Wen Lin, Yu Tsao, Hsin-Min Wang