Cyberattack Detection System in Private Cloud

Chethan  M.S.; Girish  L.; Manjula  T.; Priya  R. Acharya; Nikki  Kishore; Chaitra  M.S.

Abstract

As cloud computing adoption in colleges continues to rise, the security of private cloud systems has become a paramount concern. Data breaches resulting from cyberattacks can inflict severe damage to a university's revenue and reputation. This research proposes a novel machine learning-based cyber threat detection system tailored to the university's private cloud environment. The system's main objective is to continuously monitor the cloud infrastructure and employ advanced machine learning algorithms to analyze network traffic, and identifying and preventing unusual activities that may indicate potential cyberattacks. By leveraging the potential of machine learning, this innovative system aims to enhance the university's cybersecurity protections. It considers the dynamic and evolving nature of cyber threats, enabling real-time detection and proactive measures against malicious activities. The integration of cutting-edge machine learning models and feature extraction techniques empowers the system to identify patterns of anomalous behavior, even in the face of sophisticated attacks. Essential elements of the suggested system encompass the analysis of network traffic, the identification of anomalies, and the incorporation of threat intelligence. Through the analysis of network packets and access logs, the system can effectively detect signs of unauthorized access, data exhilaration, and other cyber threats. Additionally, threat intelligence feeds provide the system with up-to-date information on emerging threats, enabling quick responses to potential risks. Moreover, the system's implementation adheres to privacy and data protection regulations, ensuring secure handling of sensitive information within the private cloud environment. Regular updates and adaptive learning capabilities enable the system to evolve with changing cyber threats, ensuring continued robustness in the face of new challenges. In conclusion, the proposed machine learning-based cyberattack detection system presents a powerful solution to safeguarding the university's private cloud infrastructure. By promptly detecting and mitigating potential cyber threats, the system acts as a proactive defense mechanism, safeguarding valuable data and preserving the university's reputation in the ever-evolving landscape of cyber security.

Abstract

Keywords