Loading...
Market
What will be the impact of the vulnerability in Prompt-Guard-86M AI model on Meta's stock price by end of 2024?
2
Resolution / Starting Odds
Increase • 25%
Decrease • 25%
No significant change • 25%
Other • 25%
Stock market data from financial news sources
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
Increase over 5% • 25%
Decrease over 5% • 25%
Stable (+/- 5%) • 25%
Volatile (fluctuations over 10%) • 25%
Increase by more than 5% • 25%
Increase by 0-5% • 25%
Decrease by 0-5% • 25%
Decrease by more than 5% • 25%
Stock price increases by more than 10% • 25%
Stock price decreases by more than 10% • 25%
Stock price remains within 10% range • 25%
Insufficient data • 25%
Increase over 10% • 25%
Increase up to 10% • 25%
No significant change • 25%
Decrease • 25%
Increase by >10% • 33%
Increase by <=10% • 33%
No significant impact • 33%
Increase by more than 10% • 33%
Increase by less than 10% • 33%
Decrease • 33%
Yes • 50%
No • 50%
Decrease by more than 10% • 25%
Decrease by 5-10% • 25%
No significant change (within ±5%) • 25%
Increase by more than 5% • 25%
Higher by more than 10% • 25%
Within ±10% range • 25%
Lower by more than 10% • 25%
Lower by more than 20% • 25%
