Completed
Jailbreak attacks to avoid Safety Guardrails
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
LLM Security 101 - Risks, Attacks, and Mitigation Strategies
Automatically move to the next video in the Classroom when playback concludes
- 1 LLM Security Risks
- 2 Video Overview
- 3 Resources and Scripts
- 4 Installation and Server Setup
- 5 Jailbreak attacks to avoid Safety Guardrails
- 6 Detecting jailbreak attacks
- 7 Llama Guard and its prompt template
- 8 Llama Prompt Guard
- 9 Testing Jailbreak Detection
- 10 Testing for false positives with Llama Guard
- 11 Off-topic Requests
- 12 Prompt Injection Attacks Container escape, File access / deletion, DoS
- 13 1. Detecting Injection Attacks with a Custom Guard
- 14 Preventing Injection Attacks via User Authentication
- 15 37 Using Prepared Statements to avoid SQL Injection Attacks
- 16 Response Sanitisation to avoid Injection Attacks
- 17 Malicious Code Attacks
- 18 Building a custom classifier for malicious code
- 19 Using Codeshield to detect malicious code
- 20 Malicious Code Detection Performance
- 21 Effect of Guards/shields on Response Time / Latency
- 22 Final Tips
- 23 Resources
