EPISODE · Oct 31, 2023 · 51 MIN
Steve Wilson and Gavin Klondike -- OWASP Top Ten for LLM Release
from The Application Security Podcast · host Chris Romeo
The first OWASP Top 10 for Large Language Model Applications gave developers and security teams a shared threat model for a rapidly changing technology. Project leaders Steve Wilson and Gavin Klondike walk through the inaugural list and explain why familiar controls need to be reconsidered around probabilistic systems. They cover prompt injection, insecure output handling, training-data poisoning, denial of service, supply-chain vulnerabilities, sensitive information disclosure, insecure plugin design, excessive agency, overreliance, and model theft. Along the way, they distinguish application risks from attacks on the underlying model and show how plugins and autonomous actions can enlarge the blast radius. The episode closes with what the project learned from community feedback and how the list would evolve as real-world LLM deployments exposed new failure modes.The Application Security Podcast is brought to you by Security Journey.About Security JourneySecurity Journey provides application security education for developers and everyone in the software development lifecycle.→ Learn more about Security JourneyConnect with Steve Wilson and Gavin Klondike:→ Steve Wilson on LinkedIn→ Gavin Klondike on LinkedIn→ OWASP GenAI Security ProjectMentioned in this episode:→ OWASP Top Ten for LLM Applications project homepage→ OWASP Top 10 For LLMs 2023 Slides V1 1→ ChatGPT→ LangChain→ Tay (Microsoft chatbot)→ DEF CONFollow the Application Security Podcast:➜ Home➜ X➜ LinkedIn➜ YouTube➜ Instagram➜ FacebookChapters:00:00 Introducing the OWASP Top 10 for LLM Applications01:37 A threat model for large language models05:39 Risk 1 — Prompt injection09:00 Risk 2 — Insecure output handling11:35 Risk 3 — Training-data poisoning15:14 Risk 4 — Model denial of service19:11 Risk 5 — Supply-chain vulnerabilities28:16 Risk 6 — Sensitive information disclosure33:28 Risk 7 — Insecure plugin design38:27 Risk 8 — Excessive agency42:39 Risk 9 — Overreliance46:31 Risk 10 — Model theft49:56 Lessons for the next release
Embed this episode
What this episode covers
The first OWASP Top 10 for Large Language Model Applications gave developers and security teams a shared threat model for a rapidly changing technology. Project leaders Steve Wilson and Gavin Klondike walk through the inaugural list and explain why familiar controls need to be reconsidered around probabilistic systems. They cover prompt injection, insecure output handling, training-data poisoning, denial of service, supply-chain vulnerabilities, sensitive information disclosure, insecure plug...
Ready to play
Steve Wilson and Gavin Klondike -- OWASP Top Ten for LLM Release
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.