Bengaluru Engineering Students Build AI System To Identify Deepfake Videos

Last Updated:September 14, 2026, 12:37 IST

Designed as a web application, the prototype allows users to upload videos and receive a detection result.

EPCET Bengaluru students have developed a web-based AI system designed to identify potential deepfake videos. (AI Image)

As artificial intelligence makes manipulated videos increasingly difficult to distinguish from authentic footage, engineering students at East Point College of Engineering and Technology (EPCET), Bengaluru, have developed a web-based AI system designed to identify potential deepfake videos.

The project has been developed by Adarsh R, Chandu Kumar G, K N Siddarth and Likith Roshan H B, students of the Department of Computer Science and Engineering, under the guidance of Assistant Professor Nithyananda C R.

The system uses a hybrid artificial intelligence model that combines a ResNeXt50 Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) model. The approach analyses facial features across multiple video frames to identify patterns that may indicate manipulated content.

Designed as a web application, the prototype allows users to upload videos and receive a detection result. The project also includes an interactive algorithm visualiser intended to show how the system processes video frames and extracts features while analysing the footage.

According to the project team, the hybrid CNN-LSTM approach was able to identify deepfake videos during testing. The system is intended to demonstrate how AI-based tools can assist users in assessing the authenticity of digital content as synthetic media becomes more sophisticated.

Commenting on the project, Rajiv Gowda, CEO, East Point Group of Institutions, said deepfakes have become an issue of trust as well as technology.

“Deepfakes are no longer only a technology story; they are a trust story. What makes this project relevant is that our students are applying AI to a problem that ordinary users, businesses and institutions increasingly face – knowing whether what they see is real. Student innovation becomes meaningful when it addresses challenges that are already shaping society,” he said.

The students have identified several areas for further development, including faster processing, compatibility with additional video formats, improved detection accuracy and the ability to analyse videos containing multiple faces.

The current system is a functional prototype and is not intended to serve as a commercial or forensic-grade deepfake verification tool.

Quick Answers

Powered by

Ask News18

Which Bengaluru college developed the AI system to detect deepfake videos?

The web-based AI system was developed by engineering students at the East Point College of Engineering and Technology (EPCET) in Bengaluru.

What specific AI models are used in the Bengaluru students’ deepfake detection system?

The system utilizes a hybrid artificial intelligence model that combines a ResNeXt50 Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) model to analyze facial features across multiple video frames.

What are the future development goals for the EPCET student deepfake detection project?

The student developers have identified several areas for future improvement, including achieving faster processing, compatibility with additional video formats, improved detection accuracy, and the ability to analyze videos that contain multiple faces.

Powered by

Ask News18

About the Author

Education.Careers Desk

A team of reporters, writers and editors brings you news, analyses and information on college and school admissions, board and competitive exams, career options, topper interviews, job notifications, …Read More

Read More