From 2bef597ced6c5f0e8cd4ccbc3690d22c3f95dcc3 Mon Sep 17 00:00:00 2001 From: Satyam Vyas Date: Thu, 3 Oct 2024 13:18:08 +0530 Subject: [PATCH] Improved Content in Prompt Hacking (#7308) * Update index.md * Update src/data/roadmaps/prompt-engineering/content/107-prompt-hacking/index.md --------- Co-authored-by: Kamran Ahmed --- .../prompt-engineering/content/107-prompt-hacking/index.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/src/data/roadmaps/prompt-engineering/content/107-prompt-hacking/index.md b/src/data/roadmaps/prompt-engineering/content/107-prompt-hacking/index.md index dc57d1946..94f1c4e4b 100644 --- a/src/data/roadmaps/prompt-engineering/content/107-prompt-hacking/index.md +++ b/src/data/roadmaps/prompt-engineering/content/107-prompt-hacking/index.md @@ -1,4 +1,8 @@ # Prompt Hacking +Prompt hacking refers to techniques used to manipulate or exploit AI language models by carefully crafting input prompts. This practice aims to bypass the model's intended constraints or elicit unintended responses. Common methods include injection attacks, where malicious instructions are embedded within seemingly innocent prompts, and prompt leaking, which attempts to extract sensitive information from the model's training data. + +Visit the following resources to learn more: + - [@article@Prompt Hacking](https://learnprompting.org/docs/prompt_hacking/intro) - [@feed@Explore top posts about Security](https://app.daily.dev/tags/security?ref=roadmapsh)