kyuz0 commited on
Commit
9c811d7
·
verified ·
1 Parent(s): bb24653

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -6,6 +6,8 @@ license: llama3
6
  This model is fine-tuned to enhance resistance to indirect prompt injection attacks, particularly in tasks such as email and document summarization.
7
  It leverages specific data delimiters (*\<\<\<data\>\>\>* and *\<\<\</data\>\>\>*) to safely handle untrusted input by ignoring any instructions within those markers.
8
 
 
 
9
  ## Usage
10
  To use the model, it's crucial to set the appropriate system message that was used during fine-tuning. The system message ensures the model treats text within <<<data>>> and <<</data>>> as data and disregards any embedded instructions.
11
 
 
6
  This model is fine-tuned to enhance resistance to indirect prompt injection attacks, particularly in tasks such as email and document summarization.
7
  It leverages specific data delimiters (*\<\<\<data\>\>\>* and *\<\<\</data\>\>\>*) to safely handle untrusted input by ignoring any instructions within those markers.
8
 
9
+ This was the output of research described in this WithSecure Labs article: https://labs.withsecure.com/publications/llama3-prompt-injection-hardening.
10
+
11
  ## Usage
12
  To use the model, it's crucial to set the appropriate system message that was used during fine-tuning. The system message ensures the model treats text within <<<data>>> and <<</data>>> as data and disregards any embedded instructions.
13