The increasing complexity of cyberattacks has exposed the limitations of traditional intrusion detection systems, particularly in handling zero-day threats and minimizing false alarms. This study proposes a hybrid Intrusion Detection and Prevention System (IDPS) that integrates Supervised Learning (SL) for fast high-confidence classification with Deep Reinforcement Learning (DRL) for adaptively handling uncertain cases. The system is evaluated on two benchmark datasets: UNSW-NB15 and NSL-KDD. The hybrid model achieved 93.95% accuracy on UNSW-NB15 and 99.45% accuracy on NSL-KDD, significantly reducing false positives while maintaining balanced precision and recall. The computational time for model training and inference remained within practical limits, with end-to-end training completed in approximately 2–5 minutes. These results demonstrate the system’s potential for scalable, real-time deployment in dynamic cybersecurity environments.
Use Your Cell Phone as a Document Camera in Zoom
From Computer
Log in and start your Zoom session with participants
From Phone
To use your cell phone as a makeshift document camera
