This project aims to validate and integrate the CIC-Bell-DNS-EXF-2021 dataset within a Security Information and Event Management (SIEM) framework. Utilizing machine learning classifiers including Passive Aggressive, Cat-Boost, and AdaBoost, the study focuses on analyzing DNS records to enhance the detection and mitigation of security threats. By merging multiple CSV files into a comprehensive dataset and analyzing key DNS features such as frequency-based and entropy-based metrics, the objective is to bolster the effectiveness of SIEM systems in identifying DNS-related vulnerabilities and anomalous activities
The study titled "Analytical Validation and Integration of CIC-Bell-DNS-EXF-2021 Dataset on Security Information & Event Management" utilizes the CIC-Bell-DNS-EXF-2021 dataset, collected from Kaggle. The dataset, a combination of over ten CSV files, was merged into a single file named `merger.csv`, encompassing various frequency-based and entropy-based DNS features. Key columns include `A_frequency`, `NS_frequency`, `CNAME_frequency`, `SOA_frequency`, and several others, alongside `rr_type`, `rr_count`, and more. The investigation implemented three machine learning classifiers: Passive Aggressive Classifier, Cat-Boost, and AdaBoost, to analyse and classify DNS records effectively. The integration and validation of this dataset within a Security Information and Event Management (SIEM) framework aim to enhance the detection and mitigation of DNS-based security threats.
Keywords: Passive Aggressive Classifier, Cat-Boost, and AdaBoost.
NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Β· RAM : 8GB (min)
Β· Hard Disk : 128 GB
Β· Key Board : Standard Windows Keyboard
Β· Mouse : Two or Three Button Mouse
Β· Monitor : Any
S/W SPECIFICATIONS:
β’ Operating System : Windows 7+
β’ Server-side Script : Python 3.6+
β’ IDE : PyCharm.
β’ Libraries Used : Pandas, Numpy, Matplotlib, OS.