Jump to content

20250165589. Filtering Harmfu (Amazon Technologies, .)

From WikiPatents

FILTERING FOR HARMFUL GENERATIVE ARTIFICIAL INTELLIGENCE RESULTS

Abstract: 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.

Inventor(s): Vinayshekhar BANNIHATTI KUMAR, Sopan KHOSLA, Hayden LAWLER, Siddharth Satish GOYAL, Rashmi GANGADHARAIAH, Brijesh LUCKRIA, James W. HORSLEY, Bhaskar Hosahalli RANGASWAMY, Abhijit S. BARDE

CPC Classification: G06F21/55 (Detecting local intrusion or implementing counter-measures)

Search for rejections for patent application number 20250165589


Cookies help us deliver our services. By using our services, you agree to our use of cookies.