Optimising DOS Attacks Using Machine Learning Algorithms and Securing IOT Devices from Attacks

In today's hyperconnected world, identifying and defending against denial-of-service (DoS) attacks and securing Internet of Things (IoT) devices are increasingly crucial. Recognizing distributed denial-of-service (DDoS) attacks is essential for network security enhancement and IoT device securi...

Full description

Saved in:
Bibliographic Details
Published in:2024 International Conference on Expert Clouds and Applications (ICOECA) pp. 456 - 461
Main Authors: Siwal, Rahul, P, Sivakumar
Format: Conference Proceeding
Language:English
Published: IEEE 18.04.2024
Subjects:
ADA boost
attack detection
Blockchain for DoS/DDoS prevention
Blockchains
Computer crime
Denial of Service (DoS)
Denial-of-service attack
Extra Tree Algorithm
GradientBoost
Internet of Things
Machine learning algorithms
machine learning techniques for DoS/DDoS detection
mitigation techniques
network security
NSL _ KDD dataset for testing
Protection
Random Forest Algorithm
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In today's hyperconnected world, identifying and defending against denial-of-service (DoS) attacks and securing Internet of Things (IoT) devices are increasingly crucial. Recognizing distributed denial-of-service (DDoS) attacks is essential for network security enhancement and IoT device security. This research explores various methods to mitigate the impact of DDoS attacks, aiming to reduce the likelihood of such attacks. We intend to employ machine learning strategies such as the Random Forest Algorithm, ADAboost, Blockchain, Gradient Boost, and Extra Tree Algorithm to prevent malicious network traffic from overloading servers and causing outages. The initiative offers significant advantages, particularly in theory and statistics. We will test our system using the NSL _ KDD dataset, initially training the data and then subjecting it to a series of tests. Data will be presented using tables, graphs.
DOI:10.1109/ICOECA62351.2024.00086