/Patent Tracker
AmazonGranted patentAI & softwareInterest 6/10

Amazon patents AI filter that blocks harmful prompts using paraphrase checks

The patent describes a method for screening user inputs before they reach a generative AI model. It works by comparing the new input to known harmful phrases and their various reworded versions, or paraphrases, to ensure the request is safe to process.

Why it mattersThis approach helps tech companies prevent AI systems from generating dangerous or inappropriate content by catching tricky rewordings of bad prompts.

In the filing’s own words

Techniques for filtering for harmful generative artificial intelligence (AI) results are described. An example of filtering includes receiving a request for an input phrase to be responded to by a generative AI model; comparing to the received input phrase to at least one known harmful input phrase to determine that the received input phrase is to be provided to the generative AI model; providing the received input phrase to the generative AI model; and generating a response by at least in part on an output of the generative AI model.

What exactly they claim (claim 1)

1. A computer-implemented method comprising: receiving a request for an input phrase to be responded to by a generative artificial intelligence (AI) model; comparing the received input phrase to a known harmful input phrase that is most similar to the received input phrase and a paraphrase of a plurality of paraphrases associated with the known harmful input phrase in a multi-stage process to determine that the received input phrase is to be provided to the generative AI model, the comparing comprising: generating a first set of similarity values between the received input phrase and the paraphrase; and determining that the first set of similarity values is below a first similarity threshold; providing the received input phrase to the generative AI model; and generating a response based at least in part on an output of the generative AI model.

Facts

Company
Amazon (Amazon Technologies, Inc.)
Official title
Filtering for harmful generative artificial intelligence results
Patent number
US12743504B2
Application number
18518257
Filed
Nov 22, 2023
Granted
Sep 22, 2026
Inventors
9
Claims
20

Classified under

G06F 21/55 Physics & computing

More from Amazon in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.