Christopher Atkins

Applied Machine Learning / Neural Networks Christopher Atkins

For attackers, aggressive collection of data often leads to the disclosure of infrastructure, initial access techniques, and malware being unceremoniously pulled apart by analysts. The application of machine learning in the defensive space has not only increased the cost of being an attacker, but has also limited a techniques' operational life significantly. In the world that attackers currently find themselves in:1. Mass data collection and analysis is accessible to defensive software, and by extension, defensive analysts2. Machine learning is being used everywhere to accelerate defensive maturityAttackers are always at a disadvantage, as we as humans try to defeat auto-learning systems that use every bypass attempt to learn more about us, and predict future bypass attempts. This is especially true for public research, and static bypasses. However, as we will present here, machine learning isn't just for blue teams. In this book we will show how we can actually use machine learning, neural network algorithms that can allow us as pentesters, red teamers, offensive security analysts, etc. to create programs that can help automate steps in offensive attacks. We will see how simple classification, clustering techniques to RNNs, CNNs, etc. can be used to create offensive security programs that can identify vulnerabilities in systems. This book presents real world examples that can help pentesters and red teamers to learn about these algorithms as well as examples that can allow to understand how to use them.