Security & Ethical Hacking: Attacking Web and AI Systems

Overview

In this course you will learn how the security of web-based software, including deployed AI agents, can be compromised. Real-world attacks we study are conducted against a variety of web technologies and frameworks. In addition, we will introduce the topic of Adversarial Machine Learning (exploiting algorithms and learning techniques) in the Artificial Intelligence domain, including Language Models. We will review and study modern, cutting-edge research in this area. Course assessments are through quizzes, hands-on exercises and an exam. This course can be taken for academic credit as part of CU Boulder’s MS in Data Science or MS in Computer Science degrees offered on the Coursera platform. These fully accredited graduate degrees offer targeted courses, short 8-week sessions, and pay-as-you-go tuition. Admission is based on performance in three preliminary courses, not academic history. CU degrees on Coursera are ideal for recent graduates or working professionals. Learn more: MS in Data Science: https://www.coursera.org/degrees/master-of-science-data-science-boulder MS in Computer Science: https://coursera.org/degrees/ms-computer-science-boulder

Syllabus

Server Side Attacks

In this module, we introduce the protocols of the World Wide Web communication, history, and examine several important attack types targeting the server directly through vulnerabilities of web applications – including logic flaws not tied to a particular software weakness.

Client-Side Web Exploitation

In this module, we study exploit categories incorporating the client/browser (and assumed privileges of the client) in web attacks, including defenses and potential bypasses.

Language Model-based Agentic Systems

Function-calling language models (AI agents) present unique risks. We practice attacks on live, deployed models that have excessive agency in their server environments, presenting modern, high-level exploitation primitive in web-deployed language agents.

Advanced Topics - Adversarial AI

This module is an introduction and deep dive into more fundamental, algorithmic types of exploitation against AI systems, namely through study (and careful manipulation) of the machine learning models that power them.