���

​

Université Cadi Ayyad

Ecole Supérieure de Technologie Essaouira

جامعة القاضي عياض

المدرسة العليا للتكنولوجيا

الصويرة

​

Business Intelligence & Data Science

Machine Learning and Cybersecurity 

Presented by:

• Abdellah ELAAROUB
• Walid DAMOU
• Otmane ATANANE

Framed by:

• Mr. Adil EL FILALI

CONTENTS

• Why Machine learning?
• Defining Machine Learning
• Traditional Programming vs Machine Learning
• Process of Learning
• Machine Learning Algorithm
• Application of Machine Learning
• Decision Learning
• Machine Learning in Cyber Security 
• Software
• Conclusion
• References

Why Machine Learning?

• Develop systems that can automatically adapt and customize themselves to individual users.
• Discover new knowledge from large databases (data mining).
• Ability to mimic human and replace certain monotonous tasks.
• Develop systems that are too difficult/expensive to construct manually.

Defining Machine Learning.

• Machine learning is a method of data analysis that automates analytical model building.
• Machine learning (ML) is the study of computer algorithms that improve automatically through experience.
•  Machine learning algorithms build mathematical model based on sample data, known as "training data“.
• Machine learning is closely related to computational statistics.
• Python language suitable for a variety of tasks in machine learning.

​

Traditional Programming vs Machine Learning�

Traditional Programming

​

Data

Output

Program

​

Machine Learning

​

Data

Program

Program

​

Computer

Computer

Process of Learning

Machine Learning Algorithm

• Supervised Learning
• Regressions: learning numbers
• Classifications: learning classes
• Unsupervised Learning
• Clustering: finding groups
• Dimensionality Reductions: finding efficient representations
• Reinforcement Learning

​

Application of Machine Learning

Decision Learning

• Decision tree learning is one of the predictive modeling approaches used in machine learning.
• A decision tree can be used to visually and explicitly represent decisions and decision making. 
• It uses a decision tree to go from observations about an item to conclusions about the item's target value.
• A decision tree is drawn upside down with its root at the top.

​

Machine Learning in Cyber Security �

all security tasks can be divided into five categories:

​

• Prediction
• Prevention
• Detection
• Response
• Monitoring

​

​

​

​

​

How machine learning protect us in security world ?

Software Suites

• Python scikit learn
• MATLAB, mlpy
• Oracle data mining
• STATISTICA data miner
• Apache Mahout

Conclusion

•  Machine learning is quickly growing field in computer science.
• It has applications in nearly every other field of study.
• It is already being implemented commercially because machine learning can solve problems too difficult or time consuming for humans to solve.
• To describe machine learning in general terms, a variety models are used to learn patterns in data and make accurate predictions based on the patterns it observes.

References

• https://www.geeksforgeeks.org/machine-learning/
• https://en.wikipedia.org/wiki/Machine_learning
• https://www.tutorialspoint.com/machine_learning_with_python/machine_learning_algorithms_performance_metrics.htm
• https://www.researchgate.net/publication/2940012_Machine_Learning_Techniques_in_Spam_Filtering
• https://www.analyticsvidhya.com/blog/2017/09/machine-learning
• https://towardsdatascience.com/machine-learning-for-cybersecurity-101-7822b802790b

THANK YOU