Interface administrators, Administrators (Semantic MediaWiki), Curators (Semantic MediaWiki), Editors (Semantic MediaWiki), Suppressors, Administrators
7,785
edits
Prompt injection: Difference between revisions
no edit summary
No edit summary |
No edit summary |
||
| Line 2: | Line 2: | ||
When a user enters a [[prompt]] into a [[large language model]] like [[ChatGPT]], the creator of the [[language model]], like [[OpenAI]], often customizes the response of the language model by concatenating their own prompt onto the user's prompt. The creator's prompt is like a set of instructions that is concatenated before the start of the user's prompt and is hidden from the user. The creator's prompt provides context like tone, point of view, objective, length etc. | When a user enters a [[prompt]] into a [[large language model]] like [[ChatGPT]], the creator of the [[language model]], like [[OpenAI]], often customizes the response of the language model by concatenating their own prompt onto the user's prompt. The creator's prompt is like a set of instructions that is concatenated before the start of the user's prompt and is hidden from the user. The creator's prompt provides context like tone, point of view, objective, length etc. | ||
'''[[Prompt injection]] is when the user's prompt changes the creator's prompt | '''[[Prompt injection]] is when the user's prompt changes the creator's prompt, make the language model ignore the creator's prompt or leaks the creator's prompt.''' | ||
==Problems of Prompt Injection== | ==Problems of Prompt Injection== | ||
==How to Prevent Prompt Injection== | ==How to Prevent Prompt Injection== | ||
==Related Pages== | |||
*[[Prompt]] | |||
*[[Prompt engineering]] | |||
[[Category:Terms]] [[Category:Artificial intelligence terms]] | [[Category:Terms]] [[Category:Artificial intelligence terms]] | ||