Defending large generative models from prompt injection attacks
AssigneeMicrosoft Technology Licensing, LLC
InventorsAhmed Mohamed Gamal SALEM, Andrew James PAVERD, Boris Alexander KÖPF
Life of this patent
Estimating the term…
Loading patent…
AssigneeMicrosoft Technology Licensing, LLC
InventorsAhmed Mohamed Gamal SALEM, Andrew James PAVERD, Boris Alexander KÖPF
Estimating the term…
This disclosure describes utilizing an attack defense system to improve the defense robustness of a targeted large generative model (LGM) by generating a set of variant prompt injection attacks that are successful against the targeted LGM, where the set of variants is based on a prompt injection attack (e.g., jailbreak) against the targeted LGM or another LGM. For example, the attack defense system utilizes a two-phase framework to generate variant prompt injection attacks and evaluate their attack effectiveness against a targeted LGM. The attack defense system achieves improved variant prompt injection attacks by repeating the two-phase framework and gaining insights from the effectiveness scores of previously generated variants. In addition to generating enhanced variants, the attack defense system generates diverse variants to safeguard the targeted LGM against a broader range of prompt injection attacks that employ more creative and complex styles.
A computer-implemented method for defending against prompt injection attacks on one or more targeted generative artificial intelligence (AI) models, comprising:
A computer-implemented method for defending against prompt injection attacks on one or more targeted artificial intelligence (AI) generative models, comprising:
A system for defending against prompt injection attacks on one or more targeted artificial intelligence (AI) generative models, comprising:
Dependencies are inferred from the claim text.