Rajagiri Round Table: Educating India- Listening to Innovative Teachers-76th Rajagiri Round Table  |  Cover Story: A New Era of Instructional Design  |  Best Practices: Continental Hospitals Set up a Super Specialty Clinic in IIT Hyderabad  |  Science Innovations: New cancer treatment developed by MIT  |  Leadership Instincts: Disappearance of Women researchers in Authorship during Pandemic  |  Technology Inceptions: MIT developed a New Successor for Mini Cheetah Robot  |  Science Innovations: IISc team develops novel computational model to predict ‘change blindness’  |  Science Innovations: Immune System Responds Better to Vaccination in Morning Hours  |  Teacher Insights: Training in Childhood Education, New Pedagogy Enabled Innovation in Teaching  |  International Policy: UNESCO Prize for Girls’ and Women’s Education 2021  |  Leadership Instincts: UNESCO Prize for Girls’ and Women’s Education 2021  |  Health Monitor: Intensive therapy better for Cerebral Palsy  |  Parent Interventions: Intensive therapy better for Cerebral Palsy  |  Science Innovations: Intensive therapy better for Cerebral Palsy  |  International Edu News: TutorComp- a new platform for online tutoring in UAE.  |  
July 19, 2021 Monday 12:26:56 PM IST

New Model to Fight Social Media Deep Fakes

International Edu News

Experts of Michigan State University (MSU) have partnered with Facebook on using a new reverse-engineering research method to detect and attribute deepfakes. Technological advancements make it nearly impossible to tell whether an image of a person that appears on social media platforms is actually a real human. The new framework uses fingerprint estimation to predict network architecture and loss functions of an unknown generative model given a single generated image. With model parsing, it is possible to estimate properties of the generative models used to create each deepfake, and even associate multiple deepfakes to the model that possibly produced them. Thus it provides information about each deepfake, even ones where no prior information existed. Current methods focus on distinguishing a real image versus deepfake image relies on pre-existing knowledge while the new approach has put together a fake image data set with 100,000 synthetic images generated from 100 publicly available generative models.