Skip to content
ontologydriven
Sign out

Dictionary

Words, grammatical forms and meanings linked to the ontology.

prompt injection en · NOUN

Meanings

  1. (countable, qualifier:artificial intelligence; computer security; artificial intelligence; computer security, uncountable) A method of manipulating an artificial intelligence system by embedding malicious instructions (prompts) within input data in order to trick the model into overriding its intended behaviour or safeguards.
    • Large language models (LLMs), a trendy way of building artificial intelligence, have an inherent security problem: they cannot separate code from data. As a result, they are at risk of a type of attack called a prompt injection, in which they are tricked into following commands they should not. 2025 September 25, “How to stop AI’s “lethal trifecta””, in The Economist, →ISSN:
    • Yesterday, OpenAI announced an API for ChatGPT and posted an underlying format for the bot on GitHub, alluding to the issue of prompt injections. 2023 March 3, Chloe Xiang, “Hackers Can Turn Bing's AI Chatbot Into a Convincing Scammer, Researchers Say”, in VICE, archived from the original on 22 Mar 2023:
  2. (countable, qualifier:artificial intelligence; computer security; artificial intelligence; computer security, uncountable) A method of causing an artificial intelligence to ignore its initial instructions (often ethical restrictions) by directly giving it a particular prompt; a jailbreak.
    • Retomeli.io is a jobs board for remote workers, and the website runs a Twitter bot that spammed people who tweeted about remote working. The Twitter bot is explicitly labelled as being "OpenAI-driven", and within days of Goodside's proof-of-concept being published, thousands of users were throwing prompt injection attacks at the bot. 2022 September 21, Alex Hern, “TechScape: AI's dark arts come into their own”, in The Guardian, London: Guardian News & Media, →ISSN, →OCLC, archived from the original on 05 Feb 2023:
    • One category is what's known as a "prompt injection attack," in which users trick the software into revealing its hidden data or instructions. 2023 February 14, Will Oremus, “Meet ChatGPT's evil twin, DAN”, in The Washington Post, Washington, D.C.: The Washington Post Company, →ISSN, →OCLC, archived from the original on 19 Mar 2023:

Forms

SpellingFeaturesLabelsSource
prompt injections Number=Plur lexicographic

Relateds

jailbreaking · prompt engineering

Translations (1)

fi kehoteinjektio (Translations)

wikipedia: Prompt injection