The Indian Institute of Technology in Ropar, Punjab has developed 'FakeBuster', a deepfake detector to identify and prevent imposters from attending video conferencing and manipulated faces on social media. 

Deepfake a form of artificial intelligence which seamlessly stitches anyone in the world into a video or photo they never actually participated in.

The 'FakeBuster' is a deep learning-based solution that helps detect if a video is manipulated or spoofed during a video-conference meeting. It has been tested for its effectiveness on popular web conferencing applications - Skype and Zoom and also detecting deepfakes where faces are manipulated on social media to spread misinformation or defame persons. 

“Sophisticated artificial intelligence techniques have spurred a dramatic increase in the manipulation of media contents. Such techniques keep evolving and become more realistic. That makes detection difficult”, said Dr Abhinav Dhall, one of the members of a four-man team that developed the ‘FakeBuster’. Other members include Assistant Professor Ramanathan Subramanian and two students Vineet Mehta and Parul Gupta.

The tool was presented at the 26th International Conference on Intelligent User Interfaces, in the USA, last month. (https://arxiv.org/abs/2101.03321). 'FakeBuster' can function online and offline. It uses a 3D convolutional neural network for predicting video segment-wise fakeness scores. 'Deepfake' has been extensively trained on datasets such as Deeperforensics, DFDC, VoxCeleb, and deepfake videos created using locally captured (for video conferencing scenarios) images. 

Since the device can presently be attached with laptops and desktops only “we are aiming to make the network smaller and lighter to enable it to run on mobile phones-devices as well”, said Mr Subramanian. He said the team is working on using the device to detect fake audios also.

The solution is hopefully key to fighting deepfakes which are a rising form of concern as the emergence of deepfakes will make it increasingly difficult for the public to distinguish between what is real and what is fake, a situation that insidious actors will inevitably exploit—with potentially devastating consequences.