Moscow: A group of Computer experts at Don State Technical University (DGTU) in Russia has developed a Program that can detect fake videos and images created by DeepFake technology of the Generative Adversarial Network (GAN) algorithm.
The development comes at a time when the misuse of DeepFake and other Artificial Intelligence (AI) technologies that are used to generate fake images and videos has become a major privacy breach concerns.
Developers from the Don State Technical University (DGTU) in the Russian City of Rostov-on-Don hope that their program will help ordinary users, especially the journalists and researchers, identify fake videos and to quickly check, for example, a suspicious video with a request of urgent financial help from some supposed distant relative.
"The program is capable of detecting fake videos created with the DeepFake technology of the Generative Adversarial Network (GAN) algorithm. The new tool manages to capture signs of synthesis of human faces with neural networks in video frames with acceptable precision", DGTU developers said.
To use this mask program, developers said, simply download a fake video and run the check via the command line.
The program will identify all frames with faces in the video sequence and analyze each of them for numerous visual signs of falsehood, for example, the tension of the lips when speaking, the comparison of speech and facial expressions, as well as various technical nuances, up to unnaturally placed pixels, they said, according to Sputink.
"The program for detecting fake video content will become one of the modules of the future software complex to counteract destructive information", Prof Larisa Cherkesova, Scientific Director of the project, said. “This system will cover all types of multimedia content on the Internet: texts, both printed and handwritten, graphic images, including photographic and video files, as well as audio files,” Prof Larisa, Doctor in Physical and Mathematical Sciences and Professor at the Department of Systems Cyber security of DSTU Information, said.
"The program for detecting fake video content will become one of the modules of the future software complex to counteract destructive information", Prof Larisa Cherkesova, Scientific Director of the project, said.
“This system will cover all types of multimedia content on the Internet: texts, both printed and handwritten, graphic images, including photographic and video files, as well as audio files,” Prof Larisa, Doctor in Physical and Mathematical Sciences and Professor at the Department of Systems Cyber security of DSTU Information, said.
"(Not only fake videos) All internet content can be analyzed using artificial intelligence neural network technologies and evaluated based on its danger to the user", he added.
For all the latest News, Opinions and Views, download ummid.com App.
Select Language To Read in Urdu, Hindi, Marathi or Arabic.
