Overview / Usage

With modern technology becoming obsolete in cyber security, we need to come up with innovative ideas to increase the notch up in the fight against unauthorized access to our information and data. I will be taking help of Theano,Torch,Microsoft CNTKA framework to start with and then modify the implementation as i move in later stages of the project. I will be trying to modify various protection algorithms and try to come up with a ML algorithm that takes help of deep learning frameworks. I will also be taking help of Gensim to validate my data collection as efficiently as possible. The changes to encryption and decryption techniques will be studied thoroughly in later stages. In a manner where DNA cannot be replicated , similarly developing a neural network net around my algorithm against network intrusion will be the deciding factor in the efficiency of the modified algorithm. I will also taking help of Apache Hadoop in analyzing my stored data from cyber attacks and storing the result of my predicament in Apache Spark to make real-time decisions. The main problem in using machine learning algorithms in cyber security is the creation of an overhead which has an adverse effect on algorithm's performance. To eliminate it to a appreciable stage I will be taking help of BlueData without any changes to Hadoop or Spark framework. Finally the performance of the algorithm will be tested with the help of BigBench kit to get a full report on the project.