Questa pagina descrive il corso di dottorato “Introduction to Deep Reinforcement Learning and Application to the Intrusion Response Case”, tenuto dal Prof. Stefano Iannucci.
Date e Argomenti
- 27 aprile 14:00 (aula N14) – Introduction to Machine Learning and Deep Learning
- 29 aprile 14:00 (aula N8) – Introduction to Reinforcement Learning
- 2 maggio 16:00 (aula N14) – Introduction to Deep Reinforcement Learning
- 4 maggio 14:00 (aula N14) – Introduction to Autonomic Computing and Intrusion Response
Description
The size of computer systems is rapidly increasing, as well as their heterogeneity. As a consequence, any manual effort to cyber-defense is not only tedious and error-prone, but infeasible in most cases. Intrusion Response is a field of research that tries to automate this process, and is recently gaining traction thanks to the advances in artificial intelligence, and particularly in deep reinforcement learning.
In this course, elements of machine learning, deep learning, reinforcement learning, deep reinforcement learning will be illustrated, along with their application to common use cases. Furthermore, recent advances in Intrusion Response will be reviewed, and it will be shown how deep reinforcement learning can be used to build an Intrusion Response methodology that can deal with large and dynamic systems.
Prerequisites
Some degree of proficiency with the Python programming language. A basic knowledge of machine learning is not strictly required, but it is a plus.
Course Materials
- Textbook: A. Plaat, “Deep Reinforcement Learning”, Link identifier #identifier__150366-1https://arxiv.org/pdf/2201.02135.pdf
- Provided papers
Assignments
There will be one assignment at the end of the course, in the form of a small project, which must be presented to the instructor.