Abstract:

Addressing the problem of high rate of dropping packets in high network flow of the Snort network intrusion detection system, the author proposes a method of dynamic selfadapting multimedia data processing to reduce the packet loss rate of Snort and receives good results. In this paper, based on the preliminary studies, an idea of optimizing the 0/1 knapsack problem is applied to the main decisionmaking steps of the method of dynamic selfadapting multimedia data processing, the forward approach and the backward approach in dynamic programming are used respectively to make decisions and solve the problem from both positive and negative directions. In this way, the limited processing power of Snort can be focused on the more dangerous multimedia data packets when network traffic is in a certain range. The experiments show that the method can effectively improve the detection rate of multimedia data packets with dangerous information.

Key words: network intrusion detection system;multimedia;0/1 knapsack problem