Join us for Wild West Hackin’ Fest Deadwood virtual conference! Register Here

Workshop: Exploiting AI with Ben Bowman

Course Authored by .

Exploiting AI with Ben Bowman

Welcome to introduction to exploiting AI with Ben Bowman. In this workshop, we’ll discuss the MITRE attack framework and inherent flaws with AI and security, attack vectors, and how to make sure you know how not to deploy or handle an AI.

Course Length: 4 Hours

Includes a Certificate of Completion



Enroll Now

Next scheduled date: Content is loading, please wait.

Description

Welcome to introduction to exploiting AI with Ben Bowman. In this workshop, we’ll discuss the MITRE attack framework and inherent flaws with AI and security, attack vectors, and how to make sure you know how not to deploy or handle an AI.

This class will mostly be the offensive side of things with students getting to practice offensive techniques in a controlled environment as well as learning about tooling that exists to attack AI models. This should help students understand the risks of AI but will not teach any hands on defensive remediations, only discussion of how to potentially harden and remediate security issues.

System Requirements
  • Hardware Requirements
    • Ryzen 5 or i5 CPU with 16 GB of RAM
  • Software Requirements
    • Hypervisor(VMWare/Virtual Box) and Hugging Face.
  • VM/Lab/Student information
    • VMs will be provided to the students.

Syllabus

The Basics

    • What is AI and LLM

    • Deep Dive

    • What Attack Surfaces exist

Attack Vectors

    • Prompt Injection

    • Filter Dumping

    • Containment Breach

    • Data Poisoning

    • Training a spam classifier

    • Training a network traffic classification system

    • Model Inversion Attacks

    • Inferring Information Using a Loan Assessment AI

    • Transfer Model Attack

Preventitive Measures

    • Preventing Prompt Injection

    • Preventing Data Poisoning

    • Preventing Model Inversion Attacks

    • Preventing Transfer Model Attacks

Understanding the real world

    • Entering an Uncontrolled Environment

Tooling

    • PyRit

    • Garak

    • Playgrounds

FAQ

Who should take this workshop/prerequisites
This class is for people trying to learn about inherent risks that come with implementing AI in any facet.
Audience Skill Level
Intermediate

About the Instructor

Pixel splash background
Benjamin Bowman
"Hacker | Researcher | Speaker | Bird Enthusiast"
Bio

Ben Bowman joined the cyber security world at 12 years old. Slowly migrating from the wrong side of the field to the right side, perusing a bachelor’s in cyber operations and catching the attention of Black Hills Info Sec after appearing on NPR for hacking AI at Defcon. Follow me on GitHub: https://github.com/her3ticAVI

Related products

Shopping Cart

No products in the cart.