Peter the Great St. Petersburg Polytechnic University have developed a graph-based neural network (networks with paired connections inside) that can combat online fraud. When training the neural network, the identity of users – bank card numbers, data about the sender and receiver of funds, the type of bank card used, the characteristics of the device on which the transaction was made – were taken into account.
A new graph neural network has been trained to find specific patterns that can be used to figure out if a person is breaking the law. Therefore, one of the developers, SPbPU Institute of Cybersecurity and Information Protection Professor Daria Lavrova, explained in a comment to TASS that if a person receives a money transfer at once, the average daily transaction amount is 30 times higher. , artificial intelligence will be more likely to classify that person as a fraudster.
Source: Ferra

I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.