Performance Analysis of DDOS Attack Mitigation using ML

Performance Analysis of DDOS Attack Mitigation using Machine Learning

Implementation Plan:
—————————-

Scenario 1: (Using CCID 2019 dataset)
———————————————-

Step 1: Initially, we create a Software defined network (SDN), it consists of 20-IOT Nodes, 4 Switches and 1 Controller [Floodlight Controller] .

Step 2: Next, we collect, clean and preprocess the data from CCID 2019 dataset

Step 3:Next, we extract statistical and flow-based features based on preprocessed data.

Step 4:Next, we select the best features and train lightweight ML models using Decision Tree, Random Forest and SVM(hybrid approach).

Step 5: Next, we detect and block malicious traffic and monitor incoming flows using a controller data.

Step 6: Finally Plot the performance Metrics:

6.1: Number of IOT Nodes Vs. Detection Accuracy(%)

6.2: Number of IOT Nodes Vs. Latency (ms)

6.3: Number of IOT Nodes vs. Resource usage (%)

Scenario 2: (using LR-HR-DDoS 2024 dataset)
——————————————————

Step 1: Initially, we create a Software defined network (SDN), it consists of 20-IOT Nodes, 4 Switches and 1 Controller [Floodlight Controller] .

Step 2: Next, we collect, clean and preprocess the data from LR-HR DDoS 2024 dataset

Step 3:Next, we extract statistical and flow-based features based on preprocessed data.

Step 4:Next, we select the best features and train lightweight ML models using Decision Tree, Random Forest and SVM(hybrid approach).

Step 5: Next, we detect and block malicious traffic and monitor incoming flows using a controller data.

Step 6: Finally Plot the performance Metrics:

6.1: Number of IOT Nodes Vs. Detection Accuracy(%)

6.2: Number of IOT Nodes Vs. Latency (ms)

6.3: Number of IOT Nodes vs. Resource usage (%)

Scenario 3: (using Synthetic IOT data)
———————————————-

Step 1: Initially, we create a Software defined network (SDN), it consists of 20-IOT Nodes, 4 Switches and 1 Controller [Floodlight Controller] .

Step 2: Then, we generate synthetic SDN traffic data and collect, clean and preprocess the data .

Step 3:Next, we extract statistical and flow-based features based on preprocessed data.

Step 4:Next, we select the best features and train lightweight ML models using Decision Tree, Random Forest and SVM(hybrid approach).

Step 5: Next, we detect and block malicious traffic and monitor incoming flows using a controller data.

Step 6: Finally Plot the performance Metrics:

6.1: Number of IOT Nodes Vs. Detection Accuracy(%)

6.2: Number of IOT Nodes Vs. Latency (ms)

6.3: Number of IOT Nodes vs. Resource usage (%)

Software requirement:
—————————

1. Development Tool:

i) Mininet-2.0 or Above Version

ii) Python-2.7 or Above version

iii) Wireshark [If needed]

2. Operating System: Ubuntu 16.04 LTS (64-bit) or Above

Dataset:
———-

1) Link : https://www.kaggle.com/datasets/tarundhamor/cicids-2019-dataset (Scenario 1)

2) Link : https://www.kaggle.com/datasets/abdussalamahmed/lr-hr-ddos-2024-dataset-for-sdn-based-networks (Scenario 2)

Note:
——-

1) If the plan does not meet your requirements, provide detailed steps, parameters, models, or expected results in advance. Once implemented, changes won’t be possible without prior input; otherwise, we’ll proceed as per our implementation plan.

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

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

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

5) If you have any changes in the dataset, kindly provide us before implementation.

Related Pages