prompt injection
Word Rarity
Rare
Frequency: Zipf frequency 3.62 in modern English
30
Scrabble Score
15
Letters
4
Syllables
10
Unique Chars
Meaning
noun
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.
Countable; Uncountable
noun
A method of causing an artificial intelligence to ignore its initial instructions (often ethical restrictions) by directly giving it a particular prompt; a jailbreak.
Countable; Uncountable
Example Sentences
- "Yesterday, OpenAI announced an API for ChatGPT and posted an underlying format for the bot on GitHub, alluding to the issue of prompt injections."
- "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."
- "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."
- "One category is what's known as a "prompt injection attack," in which users trick the software into revealing its hidden data or instructions."