Found 3 bookmarks
Newest
Don’t you (forget NLP): Prompt injection with control characters in ChatGPT
Don’t you (forget NLP): Prompt injection with control characters in ChatGPT
Like many companies, Dropbox has been experimenting with large language models (LLMs) as a potential backend for product and research initiatives. As interest in leveraging LLMs has increased in recent months, the Dropbox Security team has been advising on measures to harden internal Dropbox infrastructure for secure usage in accordance with our AI principles. In particular, we’ve been working to mitigate abuse of potential LLM-powered products and features via user-controlled input.
#dropbox#EN#2023#ChatGPT#LLMs#prompt-injection
·dropbox.tech·
Don’t you (forget NLP): Prompt injection with control characters in ChatGPT
Prompt Injections are bad, mkay?
Prompt Injections are bad, mkay?
Large Language Models (LLM) have made amazing progress in recent years. Most recently, they have demonstrated to answer natural language questions at a surprising performance level. In addition, by clever prompting, these models can change their behavior. In this way, these models blur the line between data and instruction. From "traditional" cybersecurity, we know that this is a problem. The importance of security boundaries between trusted and untrusted inputs for LLMs was underestimated. We show that Prompt Injection is a serious security threat that needs to be addressed as models are deployed to new use-cases and interface with more systems. [PDF DOC] https://arxiv.org/pdf/2302.12173.pdf
#greshake#EN#2023#Prompt#Injections#prompt-injection#AI
·greshake.github.io·
Prompt Injections are bad, mkay?
Prompt Injections are bad, mkay?
Prompt Injections are bad, mkay?
Large Language Models (LLM) have made amazing progress in recent years. Most recently, they have demonstrated to answer natural language questions at a surprising performance level. In addition, by clever prompting, these models can change their behavior. In this way, these models blur the line between data and instruction. From "traditional" cybersecurity, we know that this is a problem. The importance of security boundaries between trusted and untrusted inputs for LLMs was underestimated. We show that Prompt Injection is a serious security threat that needs to be addressed as models are deployed to new use-cases and interface with more systems. [PDF DOC] https://arxiv.org/pdf/2302.12173.pdf
#greshake#EN#2023#Prompt#Injections#prompt-injection#AI
·greshake.github.io·
Prompt Injections are bad, mkay?