Book Image

Malware Science

By : Shane Molinari
Book Image

Malware Science

By: Shane Molinari

Overview of this book

In today's world full of online threats, the complexity of harmful software presents a significant challenge for detection and analysis. This insightful guide will teach you how to apply the principles of data science to online security, acting as both an educational resource and a practical manual for everyday use. Malware Science starts by explaining the nuances of malware, from its lifecycle to its technological aspects before introducing you to the capabilities of data science in malware detection by leveraging machine learning, statistical analytics, and social network analysis. As you progress through the chapters, you’ll explore the analytical methods of reverse engineering, machine language, dynamic scrutiny, and behavioral assessments of malicious software. You’ll also develop an understanding of the evolving cybersecurity compliance landscape with regulations such as GDPR and CCPA, and gain insights into the global efforts in curbing cyber threats. By the end of this book, you’ll have a firm grasp on the modern malware lifecycle and how you can employ data science within cybersecurity to ward off new and evolving threats.
Table of Contents (15 chapters)
1
Part 1– Introduction
Free Chapter
2
Chapter 1: Malware Science Life Cycle Overview
4
Part 2 – The Current State of Key Malware Science AI Technologies
8
Part 3 – The Future State of AI’s Use for Malware Science
11
Chapter 8: Epilogue – A Harmonious Overture to the Future of Malware Science and Cybersecurity
Appendix

TDA – comparing and contrasting the persistence diagrams of different software

The application of TDA and its technique of persistent homology offers a unique approach to differentiating benign software from malicious ones (malware), even amid the complexity and noise present in high-dimensional datasets.

Let’s delve into this by further expanding on the examples provided. First, consider benign software – programs designed to perform legitimate, useful tasks without causing harm to the system. When subjected to TDA, the properties of benign software tend to form certain predictable patterns. These properties, which can include binary structures, system calls, or network activity, may cluster together in the topological space. This is like how people at a social gathering might group based on shared interests or common connections. In terms of our earlier analogy, these clusters can be viewed as “mountains” on our landscape.

In the context of...