This is a news story, published by Wired, that relates primarily to Mistral AI news.
For more Ai research news, you can click here:
more Ai research newsFor more news from Wired, you can click here:
more news from WiredOtherweb, Inc is a public benefit corporation, dedicated to improving the quality of news people consume. We are non-partisan, junk-free, and ad-free. We use artificial intelligence (AI) to remove junk from your news feed, and allow you to select the best tech news, business news, entertainment news, and much more. If you like this article about Ai research, you might also like this article about
chatbots. We are dedicated to bringing you the highest-quality news, junk-free and ad-free, about your favorite topics. Please come every day to read the latest Chinese chatbot ChatGLM news, malicious instructions news, news about Ai research, and other high-quality news about any topic that interests you. We are working hard to create the best news aggregator on the web, and to put you in control of your news feed - whether you choose to read the latest news through our website, our news app, or our daily newsletter - all free!
chatbotWired
•
69% Informative
A new attack secretly commands a chatbot to gather personal information from chats and send it to a hacker.
The attack, named Imprompter , uses an algorithm to transform a natural language prompt into a hidden set of malicious instructions.
The researchers say they have a “ nearly 80 percent success rate’s” success rate.
Mistral AI says it has fixed the security vulnerability.
Mistral AI says it has security measures in place to help with user privacy.
The company treated the issue as one with “medium severity,” and its fix blocks the Markdown renderer from operating and being able to call an external URL through this process, meaning external image loading isn’t possible.
As LLM agents become more commonly used, the scope for attacks against them increases.
VR Score
63
Informative language
64
Neutral language
17
Article tone
informal
Language
English
Language complexity
62
Offensive language
not offensive
Hate speech
not hateful
Attention-grabbing headline
detected
Known propaganda techniques
not detected
Time-value
medium-lived
External references
7
Source diversity
7
Affiliate links
no affiliate links