Deepfake Classification

Inspiration

The rise of deepfake technology poses a serious threat to the integrity of information, especially during crucial events like elections. We wanted to empower users with a tool that could help them identify and combat deepfakes on social media platforms like Facebook.

What it does

Our Chrome extension actively scans users' Facebook feeds using a trained ML model to identify potential deepfake videos. It flags suspicious content and provides users with alerts, helping them to discern between authentic and manipulated media.

How we built it

We built the Chrome extension using JavaScript and integrated it with Facebook's API for feed access. The core of our solution is a machine learning model trained on a dataset of over 124,000 videos, enabling accurate deepfake detection in real-time.

Challenges we ran into

One major challenge was optimizing the ML model for real-time performance within the constraints of a browser extension. We also faced difficulties in accessing and processing Facebook feed data securely and efficiently.

Accomplishments that we're proud of

In today's world, where the threat of election fraud looms large, successfully developing a functional Chrome extension capable of real-time deepfake detection on Facebook feeds is a significant achievement. Additionally, training a robust ML model with a large dataset and seamlessly integrating it into the extension was a noteworthy accomplishment.

What we learned

Through this project, we gained valuable insights into the complexities of deepfake detection, browser extension development, and working with social media APIs. We also deepened our understanding of machine learning techniques and their practical applications in addressing real-world challenges.

What's next for Deepfake Classification

In the future, we aim to enhance the accuracy and efficiency of our deepfake detection model by incorporating advanced machine learning algorithms and techniques. Additionally, we plan to expand our extension to support other social media platforms and further educate users about the risks associated with deepfakes.

Built With

• flask
• javascript
• python
• solidity
• tensorflow