Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# katanemolabs/Arch-Guard-gpu
|
2 |
+
|
3 |
+
## Overview
|
4 |
+
The Katanemo Arch-Guard collection is a collection state-of-the-art (SOTA) LLMs specifically designed for **jailbreaking detection** tasks.
|
5 |
+
Definition: jailbreaking attempts are malicious prompts designed to alternate the intended behavior of the foundation LLM model of the application. They often violate the safety and security policies of the model.
|
6 |
+
|
7 |
+
Arch Guard is a classifier model fine-tuned based on the open source model Llama/prompt-guard-86M on an opensource corpus of jailbreaking attemps with an intention to improve
|
8 |
+
the capability of detecting jailbreaks only.
|
9 |
+
|
10 |
+
In summary, the Katanemo Arch-Function collection demonstrates:
|
11 |
+
- **State-of-the-art performance** in jailbreaking attempts detection
|
12 |
+
- Optimized **low-latency, low False Positive Rate**, making it suitable for real-time, production environments, and best user experience.
|