Intrusion detection system (IDS) is a system that tries to detect attacks as they occur or after the security of the system has been compromised. An IDS is placed at some strategic point on the network/host system and it uses network/host traffic data to secure the network/host system. Based on the type of detection, IDS can be classified into two types: misuse detection and anomaly detection. In case of misuse detection, IDS analyzes the gathered information against a large database of attack signatures previously stored to determine an attack. In case of anomaly detection, a normal state of the network traffic load, breakdown, protocol and typical packet size is defined. IDS monitors the network data flow to compare their state to the defined normal states to find out any security breach(s). In this paper, we present an exhaustive survey of the KDD CUP’99 database and different techniques for intrusion detection. The categorization can be done based on the algorithms such as fuzzy logic, neural networks, self organizing maps (SOM) and support vector machine (SVM). The database used in all these techniques is KDD CUP’99 dataset.