تطوير خوارزمية الانتقاء السلبي المناعية لكشف التطفل في مجموعة بيانات NSL-KDD

Abstract EN

With the development of communication technologies for mobile devices and electronic communications, and went to the world of e-government, e-commerce and e-banking.

It became necessary to control these activities from exposure to intrusion or misuse and to provide protection to them, so it's important to design powerful and efficient systems-do-this-purpose.

It this paper it has been used several varieties of algorithm selection passive immune algorithm selection passive with real values, algorithm selection with passive detectors with a radius fixed, algorithm selection with passive detectors, variable- sized intrusion detection network type misuse where the algorithm generates a set of detectors to distinguish the self-samples.

Practical Experiments showed the process to achieve a high rate of detection in the system designer using data NSL-KDD with 12 field without vulnerability to change the radius of the detector or change the number of reagents were obtained as the ratio between detection (0.984, 0.998, 0.999) and the ratio between a false alarm (0.003, 0.002, 0.001).

Contrary to the results of experiments conducted on data NSL-KDD with 41 field contact, which affected the rate of detection by changing the radius and the number of the detector as it has been to get the proportion of uncovered between (0.44, 0.824, 0.992) and the percentage of false alarm between (0.5, 0.175, 0.003).