Exploring the Large Language Models Open-Source Security Landscape - Yotam Perkal, Rezillion

Exploring the Large Language Models Open-Source Security Landscape - Yotam Perkal, Rezillion

Large Language Models (LLMs) have revolutionized how we create, interact with, and consume digital content. Consequently, their open-source ecosystem is gaining popularity at an abnormal rate. But are early adopters adequately addressing their security aspects and associated risks? In this talk, we will delve into the security risks of LLMs, emphasizing the need for a security-first approach to their adoption. We will explore different types of risks, present examples demonstrating how they can manifest, and offer mitigating strategies to address them. We will then present the results of an analysis we conducted using the OpenSSF Scorecard comparing the security posture of the 50 most popular LLM-based projects on GitHub to that of other widely-used open-source projects, including projects from the OpenSSF Critical Projects list. Our analysis reveals significant concerns regarding the maturity and security posture of open-source LLM projects, emphasizing the need to address the security risks inherent to these technologies as well as underscoring the importance of considering security factors when selecting or integrating software solutions.

Видео Exploring the Large Language Models Open-Source Security Landscape - Yotam Perkal, Rezillion канала OpenSSF