Intrusion Detection and Attack Classification Using Feed-Forward Neural Network

THE rapid development and expansion of World Wide Web and local network systems have changed the computing world in the last decade. The highly connected computing world has also equipped the intruders and hackers with new facilities for their
destructive purposes. The costs of temporary or permanent damages caused by unauthorized access of the intruders to computer systems have urged different organizations to increasingly implement various systems to monitor data flow in their networks These systems are generally referred to as Intrusion Detection Systems (IDSs).
Network security is becoming an issue of paramount importance in the information technology era The survey conducted in Australia reveals that while 98% of organizations experienced some form of broader computer crime or abuse, 67% suffered a computer security incident National and international infrastructure is heavily network based across all sectors. As we increasingly rely on information infrastructures to support critical operations in defense, banking, telecommunication, transportation, electric power, e-governance, and many other systems, intrusions into information systems have become a significant threat to our society with potentially severe consequences .
 An intrusion compromises the security (e.g. availability, integrity, and confidentiality) of an information system through various means. Computer systems have become so large, complex, and have assumed many important tasks that when things go wrong, it is extremely difficult to implement fixes fast enough to avoid mission critical problems. The fast growing data transfer rate, proliferation of networks, and the Internet’s unpredictability have added even more problems. Researchers are working hard to develop more efficient, reliable and self-monitoring systems, which detect problems and continue to operate fixing without human interaction. This type of approach tries to reduce catastrophic failures of sensitive systems.
There are two main approaches to the design of IDSs. In a misuse detection based IDS, intrusions are detected by looking for activities that correspond to known signatures of intrusions or vulnerabilities. On the other hand, an anomaly detection based IDS detects intrusions by searching for abnormal network traffic. The abnormal  traffic pattern can be defined either as the violation of accepted thresholds for frequency of events in a connection or as a user’s violation of the legitimate profile developed for his/her normal behavior. One of the most commonly used approaches in expert system based intrusion detection systems is rule-based analysis using  profile model. Rule-based
analysis relies on sets of predefined rules that are provided by an administrator or created by the system. Unfortunately, expert systems require frequent updates to remain current. This design approach usually results in an inflexible detection system that is unable to detect an attack if the sequence of events is even slightly different from the predefined profile. The problem may lie in the fact that the intruder is an intelligent and flexible agent while the rulebased IDSs obey fixed rules. This problem can be tackled by the application of soft computing techniques in IDSs. Soft computing is a general term for describing a set of optimization and processing techniques that are tolerant of imprecision and uncertainty. The principal constituents of soft computing techniques are Fuzzy Logic (FL), Artificial Neural Networks (ANNs), Probabilistic Reasoning (PR), and Genetic Algorithms (GAs).

There are two general categories of attacks which intrusion detection technologies attempt to identify - anomaly detection and misuse detection. Anomaly detection identifies activities that vary from established patterns for users, or groups of users. Anomaly detection typically involves the creation of knowledge bases that contain the profiles of the monitored activities. The second general approach to intrusion detection is misuse detection. This technique involves the comparison of a user's activities with the known behaviors of attackers attempting to penetrate a system. While anomaly detection typically utilizes threshold monitoring to indicate when a certain established metric has been reached, misuse detection techniques frequently utilize a rule-based approach. When applied to misuse detection, the rules become scenarios for network attacks. The intrusion detection mechanism identifies a potential attack if a user's activities are found to be consistent with the established rules. The use of comprehensive rules is critical in the application of expert systems for intrusion detection.
There are four major categories of networking attacks. Every attack on a network can be placed into one of these groupings.