The unique detector ‘Fake Buster’ has been created by researchers from the Indian Institute of Technology, Ropar, Punjab, and Monash University in Australia to detect imposters who attend virtual conferences without any awareness. It can also detect faces changed to slander or mock someone on social media.
In the current pandemic, this standalone solution allows a user (organizer) to detect if the video of another person is handled or spooled during a video conference when the majority of official meetings and activities are conducted online. That means that the technique will find out whether a webinar or virtual meeting takes place by presenting the same picture to an impostor on behalf of one of your colleagues.
“Comprehensive artificial intelligence techniques have prompted a dramatic increase in media content manipulation. These techniques continue to evolve and become more realistic. This makes it difficult to detect and can have far-reaching security consequences “Dr. Abhinav Dhall, one of the key members of the Fake Buster four-man team, said. “Over 90 percent of the precision of the tool is achieved,” Dhall says.
Dr. Dhall says that there are wide-reaching repercussions on the use of manipulated media content in the diffusion of false news, pornography, and other online content. Received by spoofing tools based on the transfer of facial expressions, he said such manipulations have been found in video calling platforms. These counterfeit facial expressions often convince the human eye and can have serious consequences. These videos, known as ‘Deepfakes,’ may also be used in real-time during online exams and work interviews.
This software platform is self-contained and has been tested on the Zoom and Skype video conferencing applications.
Fake Buster is available in both online and offline modes. The system for detecting deep fakes. “At the moment, the device can only be connected to laptops and desktop computers,” Prof. Subramanian, Associate, explained. “We want to make the network smaller and lighter, so it can run on mobile phones/devices as well.” He also stated that the
team is working on detecting fake audios with the device.
The team argues that the software platform ‘Fake Buster’ is one the first tools to recognize tax collectors in live video conferences used by detesters. The device has already been tested and will be available soon.
