Method for predicting and detecting network intrusion in a computer network
View Patent ↗A method of detecting an internet attack against a computing device is disclosed. The method of detecting an internet attack against a computing device comprising the steps of receiving a plurality of incoming network packets; extracting a plurality of incoming feature packets based on the plurality of incoming network packets; predicting a predicted incoming feature packet based on the plurality of incoming feature packets; obtaining a first classification data based on one of the incoming feature packets using a first classifier; obtaining a second classification data based on the predicted incoming feature packet by using a second classifier; and performing at least one remedy action if the first classification data or the second classification data identifies the internet intrusion attack; wherein each of the plurality of incoming feature packets and the predicted incoming feature packet comprise a plurality of incoming features and a plurality of predicted features respectively.
1. A method of detecting an internet attack against a computing device comprising the steps of:
a) receiving a plurality of incoming network packets;
b) extracting a plurality of incoming feature packets based on said plurality of incoming network packets;
c) predicting a predicted incoming feature packet based on said plurality of incoming feature packets;
d) obtaining a first classification data based on one of said incoming feature packets using a first classifier;
e) obtaining a second classification data based on said predicted incoming feature packet by using a second classifier; and
f) performing at least one remedy action if said first classification data or said second classification data identifies said internet intrusion attack;
wherein each of said plurality of incoming feature packets and said predicted incoming feature packet comprise a plurality of incoming features and a plurality of predicted features respectively.
2. The method of claim 1 , wherein said step of predicting said predicted incoming feature packet is done by carrying out a linear regression to said plurality of incoming features.
3. The method of claim 2 , wherein said first classifier and said second classifier are both support vector machine
4. The method of claim 3 further comprises a step of predicting the type of said internet attack based on said second classification data.
5. The method of claim 1 , wherein said plurality of incoming feature packets are obtained from a buffer that has 100 slots to hold said incoming feature packets.