Machine Learning-Based Adaptive Firewall for Real-Time Cloud Security

Abstract

Traditional firewalls are often static and struggle to adapt to evolving cyber threats in cloud environments. This paper introduces a machine learning-based adaptive firewall that dynamically adjusts firewall rules based on real-time threat analysis and traffic patterns. The proposed firewall leverages deep learning algorithms to identify anomalies and predict potential attacks. It employs continuous learning to adapt to new threat vectors and reduce false positives. Performance evaluations demonstrate that the adaptive firewall achieves high accuracy in detecting and blocking malicious traffic while minimizing latency. The study highlights the effectiveness of ML-based firewalls in enhancing the resilience of cloud infrastructure against sophisticated cyberattacks.