Sign inSign in
ConceptAI & ML

Prompt injection

A vulnerability where an attacker manipulates inputs to make a model execute unintended instructions.
as Andrej Karpathy defines itIndependentThe wording closest to all 3 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Language model2LLMs1Token probabilities1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

2

Each in their own terms, from the easiest level.

  • Andrej Karpathy

    Undergraduate

    An attack where hidden instructions within user-provided data hijack the LLM's intended prompt behavior.
    • 51:30Introduction to Large Language Models
  • Jim Harris

    National Capital Area Skeptics (NCAS) · Undergraduate

    A technique where carefully crafted user inputs shift token probabilities to override model safety safeguards, privacy rules, or execution restrictions.
    • 43:00Mythbusting AI: Understanding Large Language Models and Their Limitations

Lectures that assume it

1

Connections

6

The lectures that define it or assume it, and the concepts next to it.

2 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.