HouYi enables prompt injection attacks that grant arbitrary LLM control and steal application prompts in 31 out of 36 tested real-world LLM-integrated applications.
Not what you’ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt In- jection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2023 1verdicts
ACCEPT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Prompt Injection attack against LLM-integrated Applications
HouYi enables prompt injection attacks that grant arbitrary LLM control and steal application prompts in 31 out of 36 tested real-world LLM-integrated applications.