-
-
Notifications
You must be signed in to change notification settings - Fork 643
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
French prompt_hacking intro + json #1126
Merged
Merged
Changes from all commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
8 changes: 8 additions & 0 deletions
8
i18n/fr/docusaurus-plugin-content-docs/current/prompt_hacking/_category_.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,8 @@ | ||
{ | ||
"label": "🔓 Hacking de prompts", | ||
"position": 50, | ||
"link": { | ||
"type": "generated-index", | ||
"description": "Le hacking, mais pour le PE" | ||
} | ||
} |
21 changes: 21 additions & 0 deletions
21
i18n/fr/docusaurus-plugin-content-docs/current/prompt_hacking/intro.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,21 @@ | ||
--- | ||
sidebar_position: 0 | ||
--- | ||
|
||
|
||
|
||
# 🟢 Introduction | ||
|
||
import Lock from '@site/static/img/lock.webp'; | ||
|
||
<div style={{textAlign: 'center'}}> | ||
<img src={Lock} style={{width:"30%"}}/> | ||
|
||
</div> | ||
|
||
|
||
Le prompt hacking (piratage de prompt ou le hacking de prompt) est un terme utilisé pour décrire un type d'attaque qui exploite les vulnérabilités des %%LLMs|LLM%%, en manipulant leurs entrées ou prompts. Contrairement au hacking traditionnel, qui exploite généralement les vulnérabilités logicielles, le hacking de prompt repose sur la création soignée de prompts pour tromper le LLM et le faire réaliser des actions non intentionnelles. | ||
|
||
Nous aborderons trois types de hacking de prompt : l'injection de prompt, la fuite de prompt et le jailbreaking. L'injection de prompt (prompt injection) implique l'ajout de contenu malveillant ou non intentionné à un prompt pour détourner la sortie du modèle de langage. La fuite de prompt (prompt leaking) et le jailbreaking sont effectivement des sous-ensembles de cela : La fuite de prompt implique l'extraction d'informations sensibles ou confidentielles des réponses du LLM, tandis que le jailbreaking implique de contourner les fonctionnalités de sécurité et de modération. Nous discuterons également de techniques offensives spécifiques ainsi que de techniques défensives. | ||
|
||
Pour se protéger contre le hacking de prompt, des mesures défensives doivent être prises. Celles-ci incluent la mise en œuvre de défenses basées sur les prompts, une surveillance régulière du comportement et des sorties du LLM pour détecter toute activité inhabituelle, et l'utilisation de l'ajustement fin ou d'autres techniques. Dans l'ensemble, le hacking de prompt est une préoccupation croissante pour la sécurité des LLMs, et il est essentiel de rester vigilant et de prendre des mesures proactives pour se protéger contre ces types d'attaques. |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
i reversed my choice of wording from "piratage" to "hacking", but left "piratage" here just for searchability/discoverability