No abstract

No abstract

Ad hoc networks are used in heterogeneous environments like tactical military applications, where no centrally coordinated infrastructure is available. The network is required to perform self-configuration, dynamic topology management, and ensure the self-sustainability of the network. Security is hence of paramount importance. Anomaly-based intrusion detection system (IDS) is a distributed activity carried out by all nodes of the network in a cooperative manner along with other related network activities like routing, etc. Machine learning and its advances have found a promising place in anomaly detection. This paper describes the journey of defining the most suitable routing protocol for implementing IDS for tactical applications, along with the selection of the related suitable data set. The paper also reviews the latest machine learning techniques, implementation capabilities, and limitations.

In recent years ad hoc networks are widely used because of mobility and open architecture nature. But new technology always comes with its own set of problems. Security of ad hoc network is an area of widespread research in recent years. Some unique characteristics of ad hoc network itself are an immense dilemma in the way of security. In this paper we have presented study about characteristics of ad hoc network, how they are problematic in ad hoc network security, attacks in ad hoc network and brief description of some existing intrusion detection system. We have also justified why distributed intrusion detection is better for ad hoc network with comparative study of existing intrusion detections in ad hoc network. General TermsAd hoc networks, Security, IDS, DIDS.

No abstract