Explained: The OWASP Top 10 for Large Language Model Applications

OWASP Top 10 for Large Language Model Applications → ibm.biz/BdMzY4
AI for cybersecurity → ibm.biz/BdMzYR
Large Language Models (LLMs), like any new technology, are subject to the risk that "malicious actors" will abuse it for financial or other gain by attempting to circumvent built-in security measures. The well-known Open Worldwide Application Security Project or OWASP project has recently published their list of top 10 security risks for LLMs. In this video, IBM Distinguished Engineer Jeff Crume explains a subset of them and what you can do to protect you and your users.
Get started for free on IBM Cloud → ibm.biz/buildonibmcloud
Subscribe to see more videos like this in the future → ibm.biz/subscribe-now
00:00 - What is the OWASP Top 10 for LLMs?
01:25 - Prompt Injection (Direct)
03:37 - Prompt Injection (Indirect)
06:43 - Insecure Output Handling
08:55 - Training Data
11:46 - Over Reliance

[@carol-lo]

Great session as always

[@ravi4044]

Great explanation 👏🏽

[@tgau]

If I could, I'd give two 👍
Easy to understand and precise.
Thank you.

[@jeffcrume]

Thanks so much, @tgau!

[@tombesore]

Terrific content but I'd like to suggest a change in the title to "Top 3 plus Bonus!" What happened to the other 7?

[@jeffcrume]

Unfortunately, we have to keep it shorter for this format so I do the best I can with tight time constraints

[@rsharma7197]

Very good session on the 3 of the Top 10. Where can I listen to the remaining?

[@jeffcrume]

Thanks! I didn’t figure most viewers would want a video that long but you can read about the rest at the link in the description

[@tyrojames9937]

INTERESTING!😁

[@christopherpetersen342]

Your example about training data isn't actually about "training" data, since the LLM is already trained and just pulling in poisoned data at run-time. Otherwise, very good stuff...

[@Matinirx]

There's always somebody that's going to come in and gum up the works 🙃

[@jeffcrume]

It think it’s one of the immutable laws of the universe 😂

[@pankaj16octdogra]

Wow, l like video series, this is new technology Netflix

[@jeffcrume]

I’m so glad you like it! And you can’t beat the price! 😂

[@bastabey2652]

"LLM is NOT a trusted user"... ouch

[@bobanmilisavljevic7857]

🔥