Detecting Black Hole Attack in Wireless Ad Hoc Networks Based On Learning Automata

Wireless ad hoc networks are vulnerable to several attacks including packet dropping. In this kind of attack, a malicious node tries to absorb network traffic and then drop them to form a denial of service (DOS) attack. Black hole attack is a sort of DOS attack. In this attack, a malicious node advertises itself as having the shortest and freshest path to the destination. Once traffic is redirected to this node, it simply drops them. In this paper, we present a novel solution to detect the black hole attack based on learning automata (LA). By using learning automata in a random environment, nodes can learn and adopt its behaviors based on the received signals from the environment. To the best of our knowledge, our work is the first one that tries to detect black hole attack by using LA. The simulation results in NS2 show that using proposed solution, attack is detected successfully.