Cybersecurity

This page is being updated — please visit again.

My contribution in this area is the implementation of Spectral Clustering for anomaly detection in network traffic. This, because the exponential growth of network traffic has led to an increase in network anomalies such as: cyber attacks, network failures and hardware malfunctions. Detecting network anomalies is a critical task to maintain the security and stability of computer networks. Also, my expertise consists in detecting such anomalies, using support vector machine multi class, as a supervised algorithm to detect early, such anomalies in network traffic [1].

Some projects in this field where I have been working on:

“Smart cybersecurity countermeasures for the network of the future” – CICERO

Illustration of a padlock on a circuit board — [1] Cicero website: Contramedidas inteligentes de ciberseguridad para la red del futuro, https://cicerocybersecurity.com/ceit-cicero-fortalecer-ciberseguridad-entornos-industriales/

The CICERO cluster aims to address the positioning of its centers in Cervera 25 technology related to Cybersecurity, concentrating this function on the development of robust information processing systems to identify and reduce system and network vulnerabilities, based on the application of signal and data security technologies, as well as the development of network virtualization technologies and software-defined networks.

The “Ayudas Cervera para Centros Tecnológicos 2023” programme of CDTI (Centre for the Development of Industrial Technology) under the Ministry of Science and Innovation, within the research project “CICERO – Contramedidas inteligentes de ciberseguridad para la red del futuro” with grant number CER-20231019.

My contribution in this project has been focused on Detection of anomalies in the traffic network of Industrial Control Systems.

Unsupervised detection system of Cyber-attack in the network traffic

Spectral clustering is an unsupervised machine learning technique that involves grouping data points into clusters based on their similarity in a high-dimensional space. This approach involves first transforming the data points into a lower-dimensional space using a spectral embedding technique, which retains the most important features of the data. Next, a clustering algorithm is applied to the transformed data points to group them into clusters [2,3].

Brain made of glowing network connections — Cicero website: Contramedidas inteligentes de ciberseguridad para la red del futuro, https://cicerocybersecurity.com [1]

Cyber-attack detection in the network traffic

The system “Cyber-attack detection in the network traffic by supervised learning” uses commonly used machine learning classification algorithms to solve the problem by identifying the normal network traffics and attack classes [2,3].

References

Contramedidas inteligentes de ciberseguridad para la red del futuro, https://cicerocybersecurity.com/ceit-cicero-fortalecer-ciberseguridad-entornos-industriales/
1st progress report of the “CICERO – Contramedidas inteligentes de ciberseguridad para la red del futuro” with grant number CER-20231019
2nd progress report of the “CICERO – Contramedidas inteligentes de ciberseguridad para la red del futuro” with grant number CER-20231019