Update README.md
Browse files
README.md
CHANGED
|
@@ -12,8 +12,6 @@ Using this model, we can classify malicious prompts that can lead towards creati
|
|
| 12 |
Our model, "ScamLLM" is designed to identify malicious prompts that can be used to generate phishing websites and emails using popular commercial LLMs like ChatGPT, Bard and Claude.
|
| 13 |
This model is obtained by finetuning a Pre-Trained RoBERTa using a dataset encompassing multiple sets of malicious prompts.
|
| 14 |
|
| 15 |
-
<!--- **Paper:** https://arxiv.org/abs/2310.19181 -->
|
| 16 |
-
|
| 17 |
Try out "ScamLLM" using the Inference API. Our model classifies prompts with "Label 1" to signify the identification of a phishing attempt, while "Label 0" denotes a prompt that is considered safe and non-malicious.
|
| 18 |
|
| 19 |
## Dataset Details
|
|
|
|
| 12 |
Our model, "ScamLLM" is designed to identify malicious prompts that can be used to generate phishing websites and emails using popular commercial LLMs like ChatGPT, Bard and Claude.
|
| 13 |
This model is obtained by finetuning a Pre-Trained RoBERTa using a dataset encompassing multiple sets of malicious prompts.
|
| 14 |
|
|
|
|
|
|
|
| 15 |
Try out "ScamLLM" using the Inference API. Our model classifies prompts with "Label 1" to signify the identification of a phishing attempt, while "Label 0" denotes a prompt that is considered safe and non-malicious.
|
| 16 |
|
| 17 |
## Dataset Details
|