Beyond Guardrails: Defending LLMs Against Sophisticated Attacks
The Data Exchange with Ben Lorica
00:00
Navigating Security Concerns in Open-Weight Models
This chapter delves into the security risks tied to open-weight AI models from China, emphasizing the compliance fears faced by sensitive sectors like the military. The discussion introduces Model Scanner, a tool for inspecting these models and highlights the necessity of robust security measures tailored to various industries.
Transcript
Play full episode
