NSL-KDD Dataset Analysis: A Machine Learning Implementation to Detect Intrusions in the Computer Network

The internet has significantly altered society, including business transactions, while increasing security threats that require robust protection for computer resources. This research advocates for using machine learning techniques to enhance intrusion detection, moving beyond traditional rule-based...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2024 2nd International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES) s. 1 - 6
Hlavní autoři: Mishra, Nilamadhab, Mishra, Sarojananda
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 19.12.2024
Témata:
Classification
Computer networks
Ethics
Intrusion detection
Logistic regression
Machine Learning
Nearest neighbor methods
NSL-KDD
Protection
Random forests
Redundancy
Signal processing
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The internet has significantly altered society, including business transactions, while increasing security threats that require robust protection for computer resources. This research advocates for using machine learning techniques to enhance intrusion detection, moving beyond traditional rule-based systems. By selecting key features, we aim to identify intruders and network anomalies more efficiently. Researcher will investigate classification algorithms like random forest, logistic regression, and k-nearest neighbors using the NSL-KDD dataset. The approach incorporates confusion matrices for in-depth analysis to improve detection accuracy and reduce redundancy. Additionally, will examine challenges related to data quality, model interpretability, and ethical concerns about bias in machine learning.
DOI:10.1109/SCOPES64467.2024.10990794