Intrusion Detection Systems (IDS) play a crucial role in network security by monitoring network traffic for suspicious activity and potential threats. With the increasing frequency and sophistication of cyber-attacks, an IDS can help organizations identify unauthorized access attempts, malware, and other security breaches in real-time. The ability to detect and respond to intrusions quickly is vital for preventing data breaches and minimizing damage.
With the rise of network attacks, detecting intrusions early is crucial for preventing data breaches and minimizing damage. Traditional signature-based intrusion detection is no longer sufficient, as new attack methods evolve constantly. The challenge is to develop an Intrusion Detection System (IDS) that can identify abnormal network activity through machine learning techniques, which are capable of recognizing unknown threats
The objective of this lab activity is to apply machine learning techniques (Logistic Regression, K Nearest Neighbor (KNN), Naïve Bayes, Decision Tree, and Random Forest) to the NSL-KDD dataset to build an IDS that can classify network traffic as either normal or malicious (attack). Then evaluate and compare model performance in terms of accuracy and efficiency.