AI Hacking 101
5 Based on 213 reviews- 51,051 Learners
- 287 Courses
The AI Hacking 101 ILT teaches students the fundamentals of penetration testing AI/LLM based applications such as customer facing chatbots.
Request More InfoThe course focuses on demonstrating how to detect and exploit common AI vulnerabilities such as:
- Prompt Injection
- Sensitive Information Disclosure
- Improper Output Handling
- System Prompt Leakage
- Misinformation
- Excessive Agency
Not only will students learn about these exploits, but they will also spend hands-on time in a custom-built environment exploiting and uncovering these vulnerabilities. The online lab features the TCM Vulnerable Chatbot, a customer service chatbot that can interact with customers' tickets and improve its responses via Retrieval Augmented Generation (RAG) using the company's knowledge base.
Who should attend AI Hacking 101 Course
- Penetration testers looking to add AI/LLM pen testing to their tool kit
- Developers working with AI and LLM applications
- Defenders looking to understand AI risks and how they can impact their organizations
- Anyone interested in AI and its risks and dangers
Prerequisites for AI Hacking 101 Course
AI Hacking 101 Course Outline
Resources
FAQs on AI Hacking 101
The course covers AI fundamentals and terminology, AI threat modeling, reconnaissance and model fingerprinting, prompt injection and jailbreaking techniques, tools for prompt injection, bypassing input/output filtering protections, and testing for harmful outputs like hate speech and misinformation.
This course is designed for penetration testers wanting to add AI/LLM testing skills, developers building AI and LLM applications, security defenders assessing AI risks to their organizations, and anyone interested in understanding AI risks and dangers.
A preliminary understanding of penetration testing methodology is suggested before taking this course.
You will learn hands-on techniques for AI model fingerprinting, executing prompt injection and jailbreak attacks, using specialized tools and prompt repositories, and bypassing common security protections implemented in AI applications.
Yes, the course begins with a fundamentals review of AI concepts and terminology, making it accessible to those new to AI security, though basic penetration testing knowledge is recommended.