Our Algorithm will be soon uploaded , above are some algorithms which I tried on NSL-KDD dataset.
Aim of this project is to develop an algorithm which has better performance than the existing methods.This project is basically detecting any unauthorised intruder in the network.This intruder can be through DDOS, Probe attack, U2R ,R2L attacks,etc.NSL-KDD and CIC-NID-2017 datasets have been used for training the models.
My contribution:-
-Applying different combination of algorithms on the two datasets.
-Tuning the hyperparameters of the model
-Applying Ensemble method
References:
R. Vinayakumar, K. P. Soman, Prabaharan Poornachandran: Applying convolutional neural network for network intrusion detection. ICACCI 2017: 1222-1228 https://ieeexplore.ieee.org/abstract/document/8126009
R. Vinayakumar, K. P. Soman, Prabaharan Poornachandran: Evaluating effectiveness of shallow and deep networks to intrusion detection system. ICACCI 2017: 1282-1289 https://ieeexplore.ieee.org/document/8126018
R. Vinayakumar, K. P. Soman, Prabaharan Poornachandran: Evaluation of Recurrent Neural Network and its variants for Intrusion Detection System (IDS)" has accepted in Special Issue On Big Data Searching, Mining, Optimization & Securing (BSMOS) Peer to Peer Cloud Based Networks in IJISMD https://www.igi-global.com/article/evaluation-of-recurrent-neural-network-and-its-variants-for-intrusion-detection-system-ids/204371
https://github.com/jvmancuso/DeepIDS XIANWEI GAO , CHUN SHAN , CHANGZHEN HU, ZEQUN NIU , AND ZHEN LIU:An Adaptive Ensemble Machine Learning Model for Intrusion Detection