CTCT-CT2
/

changeway_guardrails

Model card Files Files and versions

JiaqiWei commited on Jul 25

Commit

c09caae

·

verified ·

1 Parent(s): ff25607

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ To mitigate these risks, we developed the ChangeWay Guardrails, an external secu
 (1) detect and filter malicious user inputs, including externally injected prompts that could manipulate the model;
 (2) monitor and analyze the model’s outputs to prevent the generation of harmful discourse or unsafe executable code.
-The ChangeWay Guardrailsconsist of three key functional modules:
 1. **Prompt Injection Attack Detection**
 2. **Sensitive Information Leakage Prevention**

 (1) detect and filter malicious user inputs, including externally injected prompts that could manipulate the model;
 (2) monitor and analyze the model’s outputs to prevent the generation of harmful discourse or unsafe executable code.
+The ChangeWay Guardrails consist of three key functional modules:
 1. **Prompt Injection Attack Detection**
 2. **Sensitive Information Leakage Prevention**