DeapSECURE module 3: Machine Learning

In this lesson module, we will introduce machine learning techniques which have been applied to address pressing challenges in the area of cybersecurity.

Website: https://deapsecure.gitlab.io/deapsecure-lesson03-ml

Objectives

Here are our objectives for this module:

Understanding how machine learning can be employed to detect running applications on a smart phone.
Understanding fundamentals of decision tree and support vector machine algorithms for classification.
Practical familiarity with classification algorithms.
Practical experience with speeding up classification algorithms using parallel computer.

Prerequisites

Python programming knowledge If you have never learned Python before, we recommend the following lesson: “Plotting and Programming in Python” by Software Carpentry. For other learning resources, please visit our blog.

Schedule

	Setup	Download files required for the lesson
00:00	1. Introduction to Machine Learning	What is exactly machine learning? What can be accomplished by computers through machine learning? What are the different types of machine learning?
00:00	2. An Introduction to Scikit-Learn and Pandas	What is Scikit-Learn? What is Pandas?
00:00	3. Case Study 1: Smartphone Application Classification	What are the steps to do on a given dataset before performing machine learning?
00:00	4. Data Preprocessing for Machine Learning	What are the preparation steps to make raw data ready for machine learning? How do we clean data? What is feature selection and how do we do it? How do we prepare labels for machine learning?
00:00	5. Machine Learning for Smartphone Application Classification	What are some examples of classic machine learning algorithms? How do the classic machine learning algorithms work? How to construct a classic machine learning model in scikit-learn?
00:40	6. Tuning the Machine Learning Model	What is model tuning and why do we need it? What are the key procedures to tune a machine learning model for the best performance? What are the hyperparameters that we need to adjust in the tuning process?
01:20	7. Scaling Out: Extreme-scale Machine Learning	How can I perform machine learning on extremely large datasets? What can be accomplished by computers through machine learning?
01:20	8. Closing Words: Where Do We Go from Here?	What are some advice for newcomers in machine learning? What are possible pitfalls of machine learning?
01:20	9. Case Study 2: Drone RF Signal Classification	What are the steps to do on a given dataset before performing machine learning?
01:20	10. Machine Learning for Drone Signal Classification	How one would use Scikit-Learn to perform machine learning?
01:20	Finish

The actual schedule may vary slightly depending on the topics and exercises chosen by the instructor.