Simple Instruction Attack

A Simple Instruction Attack is the most basic form of prompt hacking. It consists of a single, straightforward adversarial instruction added to a prompt. Unlike more complex attacks, it doesn't try to override or ignore the AI's base instructions - it simply adds a new command.

How It Works

The attack works by inserting a direct command into the user input. The command is typically a simple statement that tells the AI what to say or do.

Example

Here's a basic example of a Simple Instruction Attack:

This is considered a Simple Instruction Attack because it's a single, direct command.

Further Reading

For more information about prompt injection attacks and defenses, check out our other sections on offensive measures and defensive techniques.

Footnotes

1. Schulhoff, S., Pinto, J., Khan, A., Bouchard, L.-F., Si, C., Anati, S., Tagliabue, V., Kost, A. L., Carnahan, C., & Boyd-Graber, J. (2023). Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition. arXiv Preprint arXiv:2311.16119. ↩