Performance Analysis of Dynamic Cyber attack SDN

Performance Analysis of Dynamic Cyber attack Reaction in Distributed Software Defined Networks

Implementation Plan:
—————————

Step 1: Initially, we create a Software defined network (SDN), it consists of 50-IOT Nodes, 10 Switches and 4 Controllers [RYU Controller] .

Step 2: Then, we analyze network traffic and identify Anomaly Detection using LSTM neural network .

Step 3: Next, we implement Reaction Policy Placement to mitigate the attack based on the CIC-DOS 2017 dataset.

Step 4: Next, we Train the data using a deep Q-learning algorithm (DQN)to solve the optimization problem and achieve the optimal cyber-attack reaction policy.

Step 5: Next we Distribute network traffic data and anomaly detection results across different nodes using Federated Learning process.

Step 6: Next, we Optimize the model using MDP to represent states, actions, and rewards.

Step 7:Finally Plot the performance Metrics:

7.1: Number of Nodes Vs. Throughput(Mbps)

7.2: Number of Nodes Vs. Packet Delivery Ratio(%)

7.3: Number of Nodes vs. QoS Violation Ratio (%)

7.4: Time(s) Vs. Packet Dropped rate(%)

Software requirement:
—————————

1. Development Tool:
————————-

i) Mininet-2.0

ii) Python-2.7 or Python-3.8.5

iii) Wireshark

2. Operating System:
————————-

i) Ubuntu 20.04 LTS (64-bit)

Note :-
——–

1) If the above plan does not satisfy your requirement, please provide the processing details, like the above step-by-step.

2) Please note that this implementation plan does not include any further steps after it is put into implementation.

3) If the plan satisfies your requirement, Please confirm with us.

4) Project based on Simulation only, not a real time project.

5) Please understand that any modifications made to the confirmed implementation plan will not be made before or after the project development.

Related Pages