101. A comprehensive survey of detecting deepfakes techniques.
- Author
-
Maske, Dheeraj, Munot, Satyam, Mugut, Aman, and Mundada, Girish
- Subjects
- *
GENERATIVE adversarial networks , *CONVOLUTIONAL neural networks , *DEEPFAKES , *ALGORITHMS , *COST effectiveness - Abstract
Recent advancements in technology have led to the proliferation of deepfakes. Deepfakes, AI-generated fake videos, pose a significant threat by spreading misinformation. This survey paper offers a comparative study of various techniques employed in detecting deepfake content. Through a systematic examination of algorithms such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and hybrid models, the study provides valuable insights into their strengths, limitations, and applicability. It also explores innovative methods like Blockchain-based Traceability, Lip Sync Detection, and Human-in-the-Loop Verification encompasses parameters like efficiency, robustness, and cost-effectiveness, aiding readers in understanding the nuanced complexities of deepfake detection. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF