Information Security

This research focuses on creating a robust model for detecting texts produced by large language models popular in the field of natural language processing, based on the assumption that machine learning technology can detect machine learning technology. The first study explores the field of cyber security and highlights the potential risks associated with using AI-generated texts in malicious ways.

The researcher created different types of denial-of-service attacks and applied modified algorithms to the data after calculating statistical features based on time difference between payloads passing through the encrypted channel, and tested multiple types of traditional and deep learning algorithms. This is to examine their efficiency in distinguishing four types of attacks and improve detection accuracy. Inter arrival time was calculated, which is the time difference between each two successive loads.

The use of the Internet has become a daily thing that a person can easily practice through several means, such as desktop and laptop computers, mobile phones, as well as many home devices. This widespread use has led to a significant increase in various electronic attacks, perhaps the most famous and dangerous of which are ransomware viruses. The danger of these viruses lies in the targets they seek to attack, as they are not limited to ordinary people, but rather they attack hospitals, private and government institutions, companies, educational institutions, and many other targets.