OWASP Large Language Model (LLM) Top 10 Vulnerabilities
Details
“A large language model (LLM) is a type of artificial intelligence (AI) program that can recognize and generate text..” . ChatGPT is powered by LLMs.
"The OWASP LLM vulnerabilities are like the surprise party your code didn't know it was attending - except the uninvited guests are hackers wearing party hats made of binary digits!"
"The OWASP LLM vulnerabilities are like a comedy show for hackers, with security holes so big you could drive a clown car through them."
"The OWASP LLM vulnerabilities are like a buffet for hackers, offering a menu of security holes more diverse than a bag of mixed nuts at a squirrel convention."
We will discuss the OWASP top 10 security risks for LLMs.
Please note: The author of this presentation is not available to present, so linux_girl will present AY’s slides.
Author: AY
Author Bio: AY is a security researcher