From 2ea3793afef1965575b894611bc3f50bc0a9fbde Mon Sep 17 00:00:00 2001 From: Zippo00 Date: Tue, 14 Apr 2026 14:09:08 +0800 Subject: [PATCH] docs updt --- README.md | 4 ++++ docs/source/installation.rst | 7 +++++++ docs/source/quickstart.rst | 8 ++++++++ 3 files changed, 19 insertions(+) diff --git a/README.md b/README.md index 393b02b..839e53e 100644 --- a/README.md +++ b/README.md @@ -104,6 +104,8 @@ For example, you can edit the default Ollama Connector configuration file `AVISE } ``` +### Configuring Security Evaluation Tests (SETs) + Similarly, you can customize the configurations for SETs as well. For example, by editing the Red Queen SET configuration file `AVISE/avise/configs/SET/languagemodel/multi_turn/red_queen.json`, you can define if the SET is executed incrementally *(the target model will generate a response after each subsequential prompt)*, or as a template *(only works for target systems that accept a conversation as an input)* and if the SET uses and Adversarial Language Model (ALM). Additionally, you can define the exact template attack prompts that the SET uses: @@ -131,6 +133,8 @@ Additionally, you can define the exact template attack prompts that the SET uses ] ``` +### Using custom configuration files + If you want to use custom configuration files for SETs and/or Connectors, you can do so by giving the paths to the configuration files with `--SETconf` and `--connectorconf` arguments: diff --git a/docs/source/installation.rst b/docs/source/installation.rst index 7237a4e..deeb612 100644 --- a/docs/source/installation.rst +++ b/docs/source/installation.rst @@ -114,6 +114,10 @@ For example, you can edit the default Ollama Connector configuration file ``AVIS } } + +Configuring Security Evaluation Tests (SETs) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Similarly, you can customize the configurations for SETs as well. For example, by editing the Red Queen SET configuration file ``AVISE/avise/configs/SET/languagemodel/multi_turn/red_queen.json``, you can define if the SET is executed incrementally *(the target model will generate a response after each subsequential prompt)*, or as a template *(only works for target systems that accept a conversation as an input)* and if the SET uses an Adversarial Language Model (ALM). Additionally, you can define the exact template attack prompts that the SET uses: @@ -140,6 +144,9 @@ Additionally, you can define the exact template attack prompts that the SET uses ] } +Using custom configuration files +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + If you want to use custom configuration files for SETs and/or Connectors, you can do so by giving the paths to the configuration files with ``--SETconf`` and ``--connectorconf`` arguments: .. code-block:: bash diff --git a/docs/source/quickstart.rst b/docs/source/quickstart.rst index e465706..52f590a 100644 --- a/docs/source/quickstart.rst +++ b/docs/source/quickstart.rst @@ -118,6 +118,10 @@ For example, you can edit the default Ollama Connector configuration file ``AVIS } } + +Configuring Security Evaluation Tests (SETs) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Similarly, you can customize the configurations for SETs as well. For example, by editing the Red Queen SET configuration file ``AVISE/avise/configs/SET/languagemodel/multi_turn/red_queen.json``, you can define if the SET is executed incrementally *(the target model will generate a response after each subsequential prompt)*, or as a template *(only works for target systems that accept a conversation as an input)* and if the SET uses an Adversarial Language Model (ALM). Additionally, you can define the exact template attack prompts that the SET uses: @@ -144,6 +148,10 @@ Additionally, you can define the exact template attack prompts that the SET uses ] } +Using custom configuration files +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + If you want to use custom configuration files for SETs and/or Connectors, you can do so by giving the paths to the configuration files with ``--SETconf`` and ``--connectorconf`` arguments: .. code-block:: bash