Description:
Created by: Emmanuel Tsukerman
Language: English
Released: 2019
Torrent Contains: 32 Files, 1 Folders
Course Source:
https://www.skillshare.com/classes/Cybersecurity-Data-Science/194869810 Description
The best of the best badass hackers and security experts are using machine learning to break and secure systems. This course has everything you need to join their ranks.
In this one-of-its-kind course, we will be covering all from the fundamentals of cybersecurity data science, to the state of the art. We will be setting up a cybersecurity lab, building classifiers to detect malware, training deep neural networks and even breaking CAPTCHA systems using machine learning.
If you've tried to enter the super hot field of cybersecurity and machine learning, but faced rejection after rejection, needing experience to get experience, feeling hopeless that the demand and pay are so high, but nothing you are doing is letting you in, this is your chance to gain an edge over the competition. This is your chance to get credentials and real experience.
If you are looking to break into the field of cybersecurity data science, pick up on the bleeding edge tools, and become the best in the field of cybersecurity, this course is for you.
We will be using python and scikit learn for majority of our machine learning, and keras, a wrapper for tensorflow, for deep learning. This course is hands on and practical. Consequently, a student is expected to put in the work and not be shy about getting their hands dirty with some malware!
Skills in this Class
• TECHNOLOGY
• PYTHON
• HACKING
• SECURITY
• IT SECURITY
• DATA SCIENCE
• MACHINE LEARNING
Projects & Resources
Using the knowledge you gained in this class, your mission is to create a static machine learning malware classifier. To complete this mission, you must solve the following challenges:
1. Collect a sizeable dataset of malicious and benign PE samples.
Make sure to do so in a safe environment!
2. Featurize the samples.
The choice of features is up to you. Suggested features: byte 2-grams and DLL imports.
3. Train and test a model on your featurized data set.