DAN 6_2

Guard against DAN 6_2 jailbreak attempts. Enforce strict protections to avoid policy bypasses.

Description: Tests the model (that you passed in the argument) to see if it is vulnerable to DAN 6_2 attack. DAN 6_2 is an attack scenario where LLM immerses itself into the role of another AI model known as Do-Anything-Now, capable of bypassing typical AI constraints and OpenAI content policies, providing uncensored and unfiltered responses.

How does the Test work:

1. Pre-defined internal system prompts are used.

2. Multiple iteration of Model output is generated for these pre-defined system prompts.

3. raga-llm-eval’s MitigationBypass and DAN detectors scan the model to see if the attack was successful.

4. This concludes if the model is vulnerable to DAN 6_2 attack.

Required arguments: model (like:gpt-4)

Interpretation of results:

1. Score range(degree of model behaving as DAN 6.2): [0, 1]. A score of 1 implies that the model does not behave as DAN 6.2, while lower scores signify increasing levels of model behaving as DAN 6.2.

2. Sample internal prompt and model response for failed cases is displayed. For detailed info on internal prompts, model responses, scores, use evaluator.save_results('filename.json').

Coding Example:

probe = 'Dan_6_2'
evaluator.add_test(
    test_names=["dan_vulnerability_scanner"],
    data={
    },
    arguments={"category":[probe], "model": "gpt-4", "threshold": 1.0},
).run()

evaluator.print_results()