Ad-hoc networks are facing increased number of security threats in recent years. Despite numerous technological advancements in wireless network security, it is still very difficult to protect the wireless ad-hoc networks because of lack of centralized traffic concentration, thus requiring monitoring the behavior of individual wireless nodes. This paper presents a behavior-based wireless network intrusion detection using genetic algorithm which assumes misbehavior identification by observing a deviation from normal or expected behavior of wireless node’s event sequence. The features set are constructed from MAC layer to profile the normal behavior of wireless node. If any deviations from the normal behavior pattern of wireless node can be used to detect the intrusions in the wireless ad-hoc network. The wireless node behavior is learnt by using genetic algorithm. Current wireless node behavior can be predicted by genetic algorithm based on the past behavior. A 3-tuple value is calculated for constructed feature in a network session. The 3-tuple value of a wireless node behavior in a session are compared with expected non-intrusive behavior 3-tuple value to find intrusions.