I Abuse Your LLM Live with 10 Security Flaws
summary
A live demo showing ten concrete security vulnerabilities in applications that use large language models (LLMs). The talk uses an existing app to uncover and exploit code-level LLM security flaws, explains what counts as an LLM security issue, clarifies the development team’s responsibilities, and presents practical secure-development best practices.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 3:06OWASP Top Ten LLM Edition
- 7:03Prompt system access flaws
- 10:38Prompt injection attacks
- 13:20Tool integration risks
- 16:10Data leakage issues
- 19:15Supply chain risks
- 23:19Data poisoning risks
- 26:38Hallucinations and biases
- 30:13RAG weaknesses
- 33:13XSS from LLM outputs
- 36:08Resource consumption risks
- 37:13GitLab Duo flaw
- 38:40Security triangle
- 40:15Q&A
