| CPC G06F 21/577 (2013.01) [G06F 2221/033 (2013.01)] | 20 Claims |

|
1. An Artificial Intelligence (AI) based filter apparatus for a generative AI model, comprising:
at least one hardware processor; and
at least one non-transitory processor-readable medium storing an input filter and an output filter executed by the at least one hardware processor,
wherein the input filter includes an input risk analyzer and the input filter:
predicts an input risk score via the input risk analyzer for a user query received from a user device, wherein the input risk score is indicative of an inclusion of harmful content in the user query; and
forwards the user query to the generative AI model based on the input risk score;
and
wherein the output filter includes an output risk analyzer and the output filter:
receives at least a model query response generated by the generative AI model for the user query;
obtains an output risk score from the output risk analyzer for the model query response; and
forwards the model query response to the user device based on a comparison of the output risk score with an output risk threshold.
|