This is my answer record of the homework in the course of Data Science for Cybersecurity, 2020@NCCU
This is the Course Link
The following is detailed description of each assignment
- Covid-19 Bonus is a data analysis exercise I did before taking this course, and the dataset used in this exercise is the Covid-19 Dataset until April 18, 2020
- Hw01 is a basic data analysis exercise with Python and ZeroAccess cyber attack dataset
- Hw02 is also a basic data analysis exercise but with Orange (Data Analysis Tool) and Network Intrusion Detection Dataset on Kaggle
- Feature Engineering
- Supervised Learning models
- K-fold Validation
- Evaluation Index
- Hw03 is an exercise about Dimension Reduction techniques, including PCA (Principal Component Analysis) and TSNE
- Hw04 is an exercise about Static Analysis and K-Means Clustering on Malware PE Files
- Hw05 is an exercise about Dynamic Analysis and Clustering on Malware profiles
- Hw06 is a more complete data analysis exercise about malware. The goal is to build a Network Intrusion Detector, a predictive model capable of distinguishing between ''bad'' connections, called intrusions or attacks, and ''good'' normal connections
- KDD Cup 99 Dataset
- Feature Engineering (Dummy variable, ADASYN Oversampling)
- Standardization & Normalization & PCA
- Classifier include KNN, Decision Tree, Random Forest, Logistic Regression, SVM and so on
- Hw07 is an exercise about Spam Mail Detector with Orange
- Hw08 is an Deep Learning exercise. In this homework, we should use CNN to classify malicious PE files into malware family
- Hw09 is an extension of Hw08. In this homework, we should use AutoEncoder to do Dimension Reduction on images, and then use CNN to classify these PE files' images into malware family
- Midterm is my answer record of the Midterm Exam. The main purpose of the Midterm Exam is to review the content learned in the first half of the semester
- Final Exam is my answer record of the Final Exam. The main purpose of the Final Exam is to review some important topics and concepts about Data Science and Cybersecurity
Note: These contents are only my personal answers, not standard answers to the homework