Treffer: Intrusion detection in campus information systems through penetration tests.

Cyber security is a crucial aspect in maintaining the integrity, availability and confidentiality of data in a system. Based on the results of the Nessus Essentials scan, the Itenas campus website was identified as having a critical vulnerability with a Base Score of 7.5 and an Impact Score of 3.6, which is categorized as High Severity. This can be exploited by attackers to gain unauthorized access to sensitive data. This research focuses on improving the security of the Itenas website using the Penetration Testing Execution Standard (PTES) method combined with a Machine Learning-based intrusion prediction model. PTES is used as a framework for conducting structured penetration testing, while an intrusion prediction model is developed using the Random Forest algorithm. This research produces a model that is able to detect various types of threats such as TCP-SYN Flood, Port Scanning, Flow Table Overflow, Blackhole Attack, and Traffic Diversion Attack with an accuracy rate of 83%. [ABSTRACT FROM AUTHOR]