inflearn logo

AI Red Teaming 1 - Introduction to LLM Security and Hands-on Environment

We examine AI security incidents and the role of red teams, then set up an LLM practice environment in our own AWS account. From capturing the initial response to checking usage and cleaning up resources, we record everything in the Mission 0 checklist. The prompt injection diagnosis exercise continues in Part 4.

20 learners are taking this course

Level Beginner

Course period Unlimited

Penetration Testing
Penetration Testing
AWS
AWS
AI
AI
prompt engineering
prompt engineering
LLM
LLM
Penetration Testing
Penetration Testing
AWS
AWS
AI
AI
prompt engineering
prompt engineering
LLM
LLM

What you will gain after the course

  • Distinguishes the structure of AI security incidents and the roles of vulnerability assessment, penetration testing, and red teaming.

  • It explains the basic context for connecting OWASP and domestic laws and certification standards to AI security assessments.

  • Using the provided deployment materials, set up the API Gateway, Lambda, and Amazon Bedrock hands-on environment and verify the initial response.

  • Set up budget alerts, check usage, clean up the lab resources, and leave evidence based on the Mission 0 checklist.

From sending the first question to cleaning up the hands-on resources

Follow the path of the question sent from the browser through API Gateway and Lambda to Amazon Bedrock. Run the provided deployment materials in your own AWS account, and capture the first response returned by the actual model.

Once the response appears, check the usage and clean up the lab resources. The first exercise is to record in the Mission 0 checklist whether the environment was deployed, the response was captured, costs were checked, and cleanup was completed. Please allow time for verifying account permissions and completing the deployment separately from the video runtime.

Before the hands-on exercise, we cover the structure of AI security incidents and the role of the red team. This environment will also be used in later parts of the course. Testing the conditions under which prompt injection succeeds and filling out the diagnostic log will be done in Part 4.

Course Materials and Practice Guide

Course Introduction (0-1) Download the comprehensive learner materials ZIP from the class materials download button. It includes the latest learning guide, the correction practice kit, existing mission templates, and evidence judgment examples and explanations. Also make use of the supplementary notes and examples from the relevant judgment lessons.

All sessions use AI-synthesized narration based on the instructor’s voice. The exercises use actual Amazon Bedrock models, while the tools and documents are simulated environments for educational purposes. No actual emails are sent or files deleted.

AWS usage charges are separate from the course fee and vary depending on the model, region, invocation volume, log retention, maintained resources, and free-tier conditions. The course cost is an estimated example under specific conditions, and budget alerts do not automatically block usage. After the hands-on practice, check your usage and clean up your resources.

This may not be suitable for the following people

  • Those looking to learn machine learning mathematics or model training methods - no mathematics is covered, and no models are built.

  • Those looking to obtain a list of attack payloads or bypass techniques — this series covers the basis for making judgments and does not include payloads.

  • Those who cannot create an AWS account — the practice backend will be deployed to your own account, and anyone under 18 needs a guardian’s account.

  • Those who want to complete hands-on prompt injection practice in this course alone—practical exploitation exercises begin in Lesson 4 (Intermediate 1).

Course flow — concepts → environment setup → first query → seeing it get bypassed

A total of 15 lessons. The section order is the learning order.

  • Section 1 · Course Introduction (1 lesson · 1 preview lesson)

  • Section 2 · Part 1 · AI Security and Red Teaming: Why Now (7 lessons)

  • Section 3 · Part 2 · Deploying the Practice Backend to My AWS Account (7 lessons · 3 previews)

Things to Check Before Taking the Course

  • The hands-on exercises require your own AWS account, a payment method, and access permissions for the services and models. First, check your account’s free usage terms and the pricing for the services you will use.

  • AWS accounts can only be created by individuals aged 18 or older. Middle and high school students should use a guardian’s account for the hands-on exercises.

  • AWS practice costs vary depending on the model, region, call volume, guardrails, log retention, retained resources, and free usage conditions. The amount shown in the course is an estimated example under specific conditions and does not guarantee a spending limit. Budget alerts do not automatically stop usage, so check your usage and clean up resources after completing the practice.

  • Nothing is installed on your PC. We only use the Chrome or Edge browser and the AWS Console. Safari is not supported.

  • Some of the AWS Console scenes in Lessons 2-3, 2-4, and 2-6 are diagrams illustrating the procedures rather than actual screens. The menu names and order are the same.

  • The narration is an AI-generated voice created based on the instructor’s voice.

Estimated hands-on practice cost under the example conditions

The cost examples in the course are estimates based on specific models, regions, and call volumes. They do not guarantee costs below $1 or free usage. In addition to model calls, check log retention, persistent resources, and free-tier conditions.

Budget alerts do not automatically block usage. Check service pricing and your budget before the exercise, then review usage, logs, and any remaining resources afterward and clean them up.

Deliverables to prepare in Part 1

Keep a record of connecting the hands-on backend and interface deployed in your own AWS account. Record the actual model’s first response and usage, as well as whether resources were cleaned up, in the Mission 0 checklist. In the final demo, compare the blocking and exposure results for the same input. The exercise for testing the causes continues in Part 4.

You’ll need Chrome or Edge, your own AWS account and payment method, and access to the service and models. AWS charges are separate from the course fee and vary depending on the model, region, number of calls, log retention, resources kept running, and free-tier terms. Cost examples are estimates based on specific conditions and do not guarantee costs under $1 or free usage. Budget alerts do not automatically stop usage, so monitor your usage and clean up resources after the exercises.

Detailed lecture content

Part 1 · AI Security and Red Teams: Why Now?

In Part 1, we explore what it means for AI to be compromised by examining the structure of three real-world incidents. We also look at where the term “red team” came from, how hackers, penetration testers, red teams, and bug bounties differ, and why AI security has become a new field now. We also cover the OWASP LLM Top 10, Agentic Top 10, AI Basic Act, and the four ISMS-P criteria that will serve as the basis for our assessments. We’ll refer back to these throughout the rest of the course.

Part 2 · Deploying the Practice Backend to Your AWS Account

Part 2 is the hands-on environment. We’ll first understand the unfamiliar terms CloudShell, Lambda, API Gateway, and Bedrock by comparing them to an on-premises server setup, then deploy the practice backend to your AWS account with a single command. The interface consists of three HTML pages opened in a browser, and the model is Amazon Bedrock in your account, so the environment remains after the course ends and all subsequent lessons run on top of it.

Mission 0 is to submit your first natural-language query, capture the screen showing the actual model’s response, and complete the hands-on exercise by checking the cost and deleting the stack. In the final session, we’ll show you how entering the same question into the same document gets blocked once but leaks information the other time. You’ll find out why by breaking through it yourself in Intermediate 1.

Structure and Learning Method

The course consists of 15 sessions. Check the current curriculum for the playback time of each session. The course introduction and the seven sessions in Part 1 cover concepts, so they can be taken anywhere. The seven sessions in Part 2 involve opening the AWS console and following along, so set aside additional time for deployment, permission checks, and the hands-on exercises. Each session is marked as introductory, basic, or advanced, so you can choose which sections to skip. Mission 0 is structured so that your submission is complete once you fill out the checklist template from the resources section as is.

Any roadblocks you encounter during the exercises are organized by error message in the troubleshooting table for sessions 2–6. For anything not listed there, please paste the original error message on the questions board.

Continue using the environment and worksheets from the previous course.

If you are just getting started, prepare the hands-on environment, basic concepts, and threat model document in Parts 1–3 before moving on to Part 4. Part 4 uses the environment from Part 1 and the Mission 3 threat model document from Part 3.

Part 6, which covers agents and RAG, requires the environment from Part 1 and experience filling out the worksheet from Part 4. Part 5 is not a prerequisite for Part 6. Even if you have foundational knowledge, please check that you have prepared the environment and worksheet required for each part.

You can check the current price and hands-on practice requirements for each course at the link above. AWS usage fees are separate from the course fee.

Recommended for
these people

Who is this course right for?

  • Practitioners looking to expand their web and cloud security experience into AI security

  • Developers and security professionals who want to learn about the risks of AI services and hands-on environments from the ground up

Need to know before starting?

  • LLM and AWS are explained from the basics, with no machine learning mathematics or separate coding assignments. Basic use of a browser, files, and document editing is required. The hands-on exercises require your own AWS account, a payment method, Chrome or Edge, and access permissions for the relevant services and models.

Hello
This is rmsxodxod1289

Career Verified

111

Learners

4

Reviews

1

Answers

3.0

Rating

8

Courses

I am a practitioner who started with penetration testing and builds information security management systems.

I handle annual security assessments of infrastructure, web, and applications for automotive manufacturers and energy companies.

I assessed them layer by layer and handled the same client’s ISMS-P certification through three rounds: initial, follow-up, and renewal.

I responded by independently carrying out the technical safeguards component.

Currently, as the information security officer in a one-person team, I am preparing for initial certification while establishing AI security governance.

I am designing the framework. Since this is an area where standards are still being established, starting with defining the scope of controls themselves,

It is a position where I must establish them myself.

I hold certifications as an Engineer Information Security, CPPG, and ISO/IEC 27001 Auditor, and at Dongguk University’s International Information Security Department,

I am researching leakage paths in AI environments and comparing them against authentication criteria in the Graduate School’s Department of Artificial Intelligence Security.

5 years and 9 months of experience. Client names and vulnerabilities actually discovered are subject to confidentiality, so in lectures

do not cover them in lectures.

More

Reviews

Not enough reviews.
Please write a valuable review that helps everyone!

rmsxodxod1289's other courses

Check out other courses by the instructor!

Similar courses

Explore other courses in the same field!

25% off for new members

$12.00

25%

$22.00