The Indian Institute of Technology in Ropar (IIT-Ropar) and Monash University in Australia have developed ‘FakeBuster’, a deepfake detector to identify and prevent imposters from attending video conferencing and manipulating faces on social media. Deepfake is a form of artificial intelligence (using deep learning) to manipulate images, audio, and videos on the Internet.
FakeBuster is a deep learning-based solution that helps detect if a video is manipulated during a video-conference meeting. Amid the pandemic, where the majority of work or meetings are online, this standalone solution enables a user to detect if another person’s video is manipulated or spoofed during a video conferencing. The software is independent of video conferencing solutions and has been tested for its effectiveness on Skype and Zoom. It also detects deepfakes where faces have been manipulated on social media, according to a report.
Sophisticated artificial intelligence techniques have spurred a dramatic increase in the manipulation of media content. Such techniques keep evolving and become more realistic, which makes detection difficult, noted 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 team claims the technology claimed that the tool has over 90% accuracy.
The tool was presented at the 26th International Conference on Intelligent User Interfaces, in the US, last month. 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.
Dr Dhall said that the usage of manipulated media content in spreading fake news has been widely observed with major repercussions. He said such manipulations have recently found their way into video-calling platforms through spoofing tools based on the transfer of facial expressions. These fake facial expressions are often convincing to the human eye and can have serious implications. These real-time mimicked visuals, or deepfakes, can even be used during online examinations and job interviews.
Since the device can presently be attached with laptops and desktops only, the team aims to make the network smaller and lighter to enable it to run on mobile phone devices as well, Subramanian informed. He said the team is also working on using the device to detect fake audios. The solution will fight deepfakes, which are a rising form of concern as its emergence 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.
The team claims that this software platform ‘FakeBuster’ is one of the first tools to detect imposters during live video conferencing using deepfake detection technology. The device has already been tested and would hit the market soon.
The demand for Chief Security Officers and other security professionals has increased over 100% in 2021 after cybersecurity emerged as one of the key concerns of CEOs after the pandemic hit the world a year ago, according to global executive search firm Kingsley Gate Partners. In 2021 alone, India will require around 70,000 people with crucial skills such as application development security, cloud security, risk management, threat intelligence, incident response, data privacy, security strategy, and health information security.