Machine Learning et Sécurité
Défense de mémoire de Trésor Detomal Remadji
Date : 20/06/2018 09:00 - 20/06/2018 10:00
Lieu : salle académique
Orateur(s) : Trésor Detomal Remadji
Organisateur(s) : Isabelle Daelman
(22) pour la détection des spams en utilisant le Pipeline afin de combiner le GridSearchCV afin de trouver les hyper paramètres du Naïve Bayes. Cette amélioration a permis d'obtenir une précision de 99% ainsi qu'un rappel de 99%.Nous allons également explorer les autres algorithmes du
Machine Leaming tels que le Support Vector Machine (SVM),l'arbre de dé cision, la Régression Logistique (RL) afin d'analyser les résultats.
The field of cybersecurity is a very broad field that aims essentially at providing pro tection Io computerized systems. Machine Learning is one of the techniques used to assist decision making in the face of various lT security issues.The key objective of using Machine Learning is to provide solutions to issues such as authentication via biometrics, intrusion detection, botnet detection, ONS tunnel detection, detection DGAs,SQL injection detection, spam detection and alert correlation. Based on (17) datasets,we proposed an implementa· tion enhancement (22) for spam detection using the Pipeline to combine the GridSearchCV to find the hyper parameters of the Naïve Bayes. This improvement resulted in precision of 99% and recall of 99% .We will also explore other Machine Leaming algorithms such as the Support Vector Machine (SVM),the decision tree,the Logistic Regression (RL) to analyze the results.
Contact :
Isabelle Daelman
-
4966
-
isabelle.daelman@unamur.be
Télecharger :
vCal