Loading...
Market
Will Meta release a new version of Prompt-Guard-86M AI model by end of 2024?
2
Resolution / Starting Odds
Yes • 50%
No • 50%
Official announcement from Meta or robusthq blog
Story
Researchers Find 99.8% Exploit in Meta's Prompt-Guard-86M AI Model
Aug 2, 2024, 03:54 PM
Researchers at robusthq have identified a significant vulnerability in Meta's recently refreshed Prompt-Guard-86M model, which is designed to protect large language models (LLMs) against jailbreaks and other adversarial examples. The exploit has a 99.8% success rate. The researchers have shared countermeasures with Meta, and the company is working on a fix. The findings were published in a blog. Additionally, a new method has been developed to enhance the security of open-source LLMs by preventing tampering, which could prevent misuse such as explaining how to make a bomb.
View original story
Similar markets
Only in the US • 25%
Only in the EU • 25%
In both the US and EU • 25%
In neither the US nor the EU • 25%
Llama 3 • 25%
A new model • 25%
No new release • 25%
Other existing model • 25%
Text-only Llama model • 25%
Multimodal Llama model • 25%
New AI model • 25%
No new model • 25%