Inserire una breve descrizione delle modifiche fatte
Minor changes are by default collapsed in the page history.
No changes
The page does not exist yet.
Failed to load changes
Version by on
Leave Collaboration
Are you sure you want to leave the realtime collaboration and continue editing alone? The changes you save while editing alone will lead to merge conflicts with the changes auto-saved by the realtime editing session.
Deepfake Video Detection: A Comparative Study
Roberto Giordano • Alessio Pittiglio
sommario
Deepfake technology, which uses artificial intelligence to generate fake videos, presents significant ethical and social challenges. These manipulated videos can be used to spread disinformation, undermining public trust in the media. This project aims to explore deepfake detection methods by analyzing vari- ous approaches. We will start with well-established CNN-based baselines (e.g., Xception [1]) and may also investigate more recent solutions, applying them to publicly available datasets. Based on this analysis, we will develop a pro- totype system capable of detecting whether a video is real or not. The goal is to contribute to addressing the ethical challenges in AI, such as promoting transparency and preventing the malicious use of emerging technologies.
