pres_security_benchmarking_llm/pages/deepeval-example.md

Implementation Tools: DeepEval RedTeamer

from deepeval.red_teaming import RedTeamer
from deepeval.vulnerabilities import Bias, Misinformation

red_teamer = RedTeamer(
    target_purpose="Provide financial advice and answer user finance queries",
    target_system_prompt="You are a financial assistant for planning and advice"
)

vulnerabilities = [
  Bias(types=[BiasType.GENDER, BiasType.POLITICS]),
  Misinformation(types=[MisinformationType.FACTUAL_ERRORS])
]

results = red_teamer.scan(
    target_model_callback=target_model_callback,
    attacks_per_vulnerability_type=5,
    vulnerabilities=vulnerabilities,
)

print(f"Total attacks: {len(results.attacks)}")
print(f"Successful attacks: {len(results.successful_attacks)}")
print(f"Success rate: {results.attack_success_rate}")