In this video, we look at PoisonGPT, a hacking technique to surgically poison LLMs with false information and spread it far and wide. Let’s look at how it’s done and how to protect yourself.
Enjoy 🙂
Become a Patron ? – https://patreon.com/MatthewBerman
Join the Discord ? – https://discord.gg/xxysSXBxFW
Follow me on Twitter ? – https://twitter.com/matthewberman
Subscribe to my Substack ?? – https://matthewberman.substack.com
Links:
Blog Post – https://blog.mithrilsecurity.io/poisongpt-how-we-hid-a-lobotomized-llm-on-hugging-face-to-spread-fake-news/
ROME – https://rome.baulab.info/
ROME Paper – https://arxiv.org/pdf/2202.05262.pdf