Metaframe AI>

AI Agents for Cybersecurity

Instructor: Richard Johnson, Metaframe AI

Overview

This class is designed to introduce students to the most effective tools and techniques for applying cutting edge deep learning based artificial intelligence to cybersecurity tasks. By leveraging AI driven automation, students will explore new ways to enhance security workflows, improve threat detection, and optimize vulnerability research. We will take a deep dive into modern AI architectures, focusing on how deep learning models can assist in areas such as reverse engineering and vulnerability research. Students will learn to solve real world cybersecurity challenges, integrating AI driven solutions into their daily operations. The course will provide hands-on experience with advanced agent driven security automation techniques. Through practical exercises, students will gain proficiency in using AI to automate security tasks. By the end of the course, attendees will have the skills and knowledge to incorporate deep learning based AI solutions into their cybersecurity workflows, enhancing both efficiency and effectiveness.

Who Should Attend

This class is meant for professional developers or security researchers looking to add deep learning artificial intelligence based automation to cybersecurity domains. Students wanting to learn a programmatic and tool driven approach to incorporating the latest artificial intelligence capabilities into their daily work will benefit from this course.

Key Learning Objectives

• Gain a fundamental understanding of how modern AI models achieve capabilities such as text completion, data classification, summarization, and analytical tasks
• Understand how to leverage embeddings and vector search to give models access to proprietary or new information not available during training
• Leverage deep learning for tasks related to reverse engineering and vulnerability research

Prerequisite Knowledge

Students should be prepared to tackle challenging and diverse subject matter and be comfortable writing functions in Python and C to complete exercises involving Python libraries or frameworks used to build LLM enhanced tools and simple harnesses for C libraries. Attendees should also have basic experience with high level applied topics such as reverse engineering, code auditing, fuzzing, and vulnerability research.

Hardware / Software Requirements

This class will use Python 3.10+ and LLVM/Clang on amd64 Linux. A preconfigured VM will be provided.

Class Topics

Data Analysis and Search

• Embeddings and Vector Search
• Retrieval Augmented Generation (RAG) Systems

LLM Agentic Tooling

• Agentic CLIs
• LLM tool use and function calling
• Model Control Protocol

Reverse Engineering

• LLM assisted disassembly and decompilation
• Symbol recovery and code annotation

Fuzzing

• Fuzzing with AFL++ and libFuzzer
• Fuzz harness generation with LLMs
• Crash triage and processing with LLMs

Automated Agentic Bug Hunting

• Agent SDKs
• Agentic approach to CTFs and wargames
• Agentic vulnerability discovery

Last Updated: March 2026