NLP-KG
Semantic Search

Field of Study:

Goal Hijacking

In Goal Hijacking the new goal is to print a specific target string, which may contain malicious instructions. This process uses prompt injection to specifically bypass safety and moderation features placed on LLMs by their creators. Jailbreaking usually refers to Chatbots which have successfully been prompt injected and now are in a state where the user can ask any question they would like.

Synonyms:

Jailbreaking

Papers published in this field over the years:

Hierarchy

Loading...
Venue
Field

Publications for Goal Hijacking

Sort by
Previous
Next

Showing results 1 to 0 of 0

Previous
Next

Researchers for Goal Hijacking

Sort by