AI Security

Jailbreaks and guardrail bypass

Chapter 5 of 5 · AI Security 100%

🎭 In 2023, ChatGPT users invented "DAN," an alter ego with no rules, just by asking it to play a character. Could you talk a refusal out of your own bot?

A jailbreak does not break your code, it bends the model's trained "no." You'll take a refusal your own bot gives, then walk past it with role-play, encoding, and splitting, measuring how often each one wins. 🔓

Premium Chapter

Create a free account to access this chapter and start learning with hands-on labs.

Create Free Account

Join 7,000+ cybersecurity learners

Ready to track your progress?

Create a free account to save your progress, earn XP, and access 170+ hands-on cybersecurity labs.

Start Learning Free

Course Progress

Track your learning journey

0 /5
0 % Complete
5 Remaining
Course Chapters

No chapters found for this filter

6
Sensitive information disclosure
Soon Available Aug 13, 2026
7
RAG and embedding attacks
Soon Available Aug 14, 2026
8
LLM agents and tool abuse
Soon Available Aug 15, 2026
9
Insecure output handling
Soon Available Aug 16, 2026
10
LLM application defense
Soon Available Aug 17, 2026
20,000+ Hackers 100+ Labs & Courses Free
Start Hacking Free