Abstract: A clustering model clusters multiple LLM prompts through a clustering model to generate multiple clusters. Multiple judge models classify the LLM prompts to obtain multiple predictions for each LLM prompt of the LLM prompts. The predictions are into a first set of security classes corresponding to at least one malicious class and a second set of security classes corresponding to at least one benign class. Multiple sample LLM prompts in a cluster are selected based on a discrepancy amongst the predictions of each sample LLM prompt in the sample LLM prompts. A lead model evaluates the sample LLM prompts to select a judge model of the judge models for the cluster. The selected judge model is assigned to the cluster.

Abstract: A clustering model clusters multiple network communications through a clustering model to generate multiple clusters. Multiple judge models classify the network communications to obtain multiple predictions for each network communication of the network communications. Multiple sample network communications in a cluster are selected based on a discrepancy amongst the predictions of each sample network communication in the sample network communications. A lead model evaluates the sample network communications to select a judge model of the judge models for the cluster. The selected judge model is assigned to the cluster.