Honeypot Analysis Using Big Data Technologies

In recent years, honeypots have become an essential tool for organizations to understand the malicious activities on the internet. They help collect patterns and activities done by intruders on the system, enabling security managers to prevent potential cyber-attacks. However, as the volume of data collected from honeypots increases, it becomes a significant challenge to analyze the data in a timely manner. It can take an extended period to identify attackers and prevent attacks, leading to a time-consuming task. To address this problem, integrating new methods of analysis or alert systems is necessary. In this work, we propose a new technique that integrates an alert system and predicts future attacks using machine learning time series algorithms such as ARIMA, SARIMAX, and big data. This technique is expected to provide more security to organizations and improve the efficiency of analysis and prevention of cyber-attacks.