Neural network learned to detect malicious bots in social networks
This algorithm will help to identify and counteract information attacks on companies that use social networks for commercial purposes. The results of the study are published in the international journal JoWUA.
The detection accuracy ranges from 60% to 90%, with false recognition accounting for 5-10%. Regarding the complex programs that the intelligence will not be able to detect - a neural network conducts regular checks of all accounts, and in one of them the bot will show itself, which will recognize it.
For example, if there are a lot of negative comments in the social network store, this development will help identify who left them, fake accounts or real people. If most of the comments were written by bots, then it will be clear to the store that an attack has taken place.
In addition, the neural network determines the quality and capabilities of bots and can understand how much money was spent on this attack. The business will have the ability to take measures to effectively respond to the incident based on the data received.
Translated with www.DeepL.com/Translator (free version)