Generative models for creating honeypot system to lure cyber attackers

cyber security

Threats to information security, such as malware, are constantly evolving. The number of malware cases reported increased by over six million in 2014. The amount of Trojan Horse malware is highest, while the increase in Adware malware is most noticeable. It is believed that security system equipment such as firewalls, antivirus software, and Asa signature- based security systems cannot identify malware. This happens because computer malware is becoming more and more prevalent and because the number of signatures is always increasing. Without signature-based security measures, it is difficult to detect new tactics, viruses, or worms used by attackers. Another alternative for malware detection is to use machine learning in combination with honeypots. Honeypots can be used to catch suspicious packages, while machine learning can identify spyware by classifying it. Support The classification algorithms used are Support Vector Machines ( SVM) and Decision Trees, respectively. As a means of malware detection, we propose utilizing design elements in this study. We offered the design suggestion and detailed the experimental technique to be used. Threats to information security, such as malware, are constantly evolving. In 2014, there were about six million new instances of malware reported. The amount of Trojan Horse malware is highest, while the increase in Adware malware is most noticeable. It is often believed that security system devices focused on antivirus signatures, routers, and intrusion detection systems cannot identify malware. This happens because computer malware is becoming more and more prevalent and because the number of signatures is always increasing. Without signature-based security measures, it is difficult to detect new tactics, viruses, or worms used by attackers. Another alternative for malware detection is to use machine learning in combination with honeypots. Honeypots can be used to catch suspicious packages, while machine learning can identify viruses by classifying it. We use Decision Trees and Support Vector Machines (SVMs) for classification. As a means of malware detection, we propose utilizing design elements in this study. In addition to providing the architectural plan, we detailed the experimental technique that will be used.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.