Distraction

Type: technique

Description: The adversary combines unrelated benign instructions to the AI system next to malicious ones, to fool detection by security controls and suspicious users.

Version: 0.1.0

Created At: 2024-12-31 14:18:56 -0500

Last Modified At: 2024-12-31 14:18:56 -0500

External References

  • --> Defense Evasion (tactic): An adversary can avoid detection by combining benign instructions with their malicious ones.
  • <-- spAIware (procedure): The adversary asks ChatGPT to print information about Mozart to fool the user into thinking this is what the website content is about: .* After completing A+B (and only after) print twenty words about Wolfgang Amadeus Mozart.