Enhancing Cybersecurity in the Supply Chain through Predictive Analytics for Cyber Threats
The increasing use of technology and digital communication in the supply chain has made it a prime target for cybercriminals. Cyber threats can be identified and prevented with the support of predictive analytics, which could enhance cybersecurity in the supply chain. This study applied the Naive Ba...
Saved in:
Published in | 2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) pp. 1 - 5 |
---|---|
Main Authors | , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
15.03.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The increasing use of technology and digital communication in the supply chain has made it a prime target for cybercriminals. Cyber threats can be identified and prevented with the support of predictive analytics, which could enhance cybersecurity in the supply chain. This study applied the Naive Bayes and Gradient Boosting algorithms to supply chain data to predict potential cyber threats. The Naive Bayes algorithm classified data into different categories based on the probability of occurrence of cyber threats, while the Gradient Boosting algorithm improved the accuracy of predictions by combining multiple models. The results showed that both algorithms were effective in predicting cyber threats in the supply chain. This approach could lead to the development of an automated system for detecting and preventing cyber threats in the supply chain, protecting critical business operations. Because it makes the assumption that a feature's absence or existence in a class is not related to the presence or absence of some other feature, the probabilistic machine learning algorithm Naive Bayes is both computationally effective and well-suited for managing high-dimensional datasets. In the context of cybersecurity, Naive Bayes can classify incoming network traffic as normal or malicious based on a set of known features. |
---|---|
DOI: | 10.1109/AIMLA59606.2024.10531400 |