Artificial Intelligence Based System Developed by Indian-Origin Scientists to Hunt Down Deepfake Videos
Realistic videos that map the facial expressions of one person onto those of another -- known as "deepfakes", present a formidable political weapon in the hands of nation-state bad actors.
Image Courtesy: Tech Spot
At a time when "deepfake" videos become a new threat to users' privacy, a team of Indian-origin researchers has developed Artificial Intelligence (AI)-driven deep neural network that can identify manipulated images at the pixel level with high precision. Realistic videos that map the facial expressions of one person onto those of another -- known as "deepfakes", present a formidable political weapon in the hands of nation-state bad actors. Led by Amit Roy-Chowdhury, professor of electrical and computer engineering at the University of California, Riverside, the team is currently working on still images but this can help them detect "deepfake" videos.
"We trained the system to distinguish between manipulated and nonmanipulated images and now if you give it a new image, it is able to provide a probability that that image is manipulated or not, and to localize the region of the image where the manipulation occurred," said Roy-Chowdhury. A deep neural network is what AI researchers call computer systems that have been trained to do specific tasks, in this case, recognize altered images. These networks are organized in connected layers; "architecture" refers to the number of layers and structure of the connections between them. While this might fool the naked eye, when examined pixel by pixel, the boundaries of the inserted object are different.
For example, they are often smoother than the natural objects. By detecting boundaries of inserted and removed objects, a computer should be able to identify altered images. The researchers tested the neural network with a set of images it had never seen before, and it detected the altered ones most of the time. It even spotted the manipulated region. "If you can understand the characteristics in a still image, in a video it's basically just putting still images together one after another," explained Roy-Chowdhury in a paper published in the journal IEEE Transactions on Image Processing. "The more fundamental challenge is probably figuring out whether a frame in a video is manipulated or not". Even a single manipulated frame would raise a red flag. Roy-Chowdhury, however, thinks we still have a long way to go before automated tools can detect "deepfake" videos in the wild. "This is kind of a cat and mouse game. This whole area of cybersecurity is in some ways trying to find better defense mechanisms, but then the attacker also finds better mechanisms."
Get the best of News18 delivered to your inbox - subscribe to News18 Daybreak. Follow News18.com on Twitter, Instagram, Facebook, TikTok and on YouTube, and stay in the know with what's happening in the world around you – in real time.
Subscribe to Moneycontrol Pro and gain access to curated markets data, trading recommendations, equity analysis, investment ideas, insights from market gurus and much more. Get Moneycontrol PRO for 1 year at price of 3 months. Use code FREEDOM.
Recommended For You
- Ashes 2019: Ben Stokes Inspires England to Miraculous Win at Headingley
- The Royal Enfield Twin Endurance Render Puts All The Right Ideas Into Our Heads
- Salman Khan Promises Tatkal Ticket to Finale in Bigg Boss 13 Promo
- Coming Out of Closet is Better Than Hiding My Relationship: Dutee Chand
- First Details of The OnePlus TV Confirmed: It Will Have a 55-Inch QLED Panel