README.md

metadata

license: unknown

Overview

Our model is designed to identify malicious prompts that can be used to generate phishing websites and emails using popular commercial LLMs like ChatGPT and Gemini. This model is obtained by finetuning a Pre-Trained RoBERTa using a dataset encompassing multiple sets of malicious prompts.

Dataset Details

The dataset utilized for training this model has been created using malicious prompts generated by GPT-4.

Training Details

The model was trained using RobertaForSequenceClassification.from_pretrained. In this process, both the model and tokenizer pertinent to the RoBERTa-base were employed and trained for 10 epochs.