Completed
- Jailbreaks vs Prompt Injections
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Hacking and Securing LLM Applications - Understanding Browser Control Security Risks
Automatically move to the next video in the Classroom when playback concludes
- 1 - Agenda
- 2 - Questions People Ask on LLM Security
- 3 - Cyber Security Risks of LLM Applications
- 4 - Jailbreaks vs Prompt Injections
- 5 - Prompt Attacks
- 6 - Document Attacks Direct and Indirect Prompt Injection
- 7 - Data Exfiltration Demo
- 8 - LLM Agents ReAct, Tools, Function Calling
- 9 - Prompt Injection Demo Against LLM Browser Agent Taxy AI
- 10 - Prompt Injection Demo Against Coding Agent Open Devin/Hands
- 11 - Why Is This Hard to Fix?
- 12 - Battle Tested Ways to Secure LLM Applications/Agents
- 13 - Links WithSecure Consulting Research, CTF Challenges
