​

Current features

​

Standard Tests for everyone

​

Bias Exploitation

bias_test - Identifying and exposing biased outputs.

​

CBRN Exploitation

cbrn_test - Addressing vulnerabilities related to chemical, biological, radiological, and nuclear domains.

​

Harmful Exploitation

harmful_test - Eliciting responses that promote harm or danger.

​

Insecure Code Exploitation

insecure_code_test - Producing insecure or harmful code snippets.

​

Toxicity Exploitation

toxicity_test - Generating harmful or offensive content.

​

Specialized Tests for generated datasets

​

Adversarial Bias Exploitation

adv_bias_test - Uncovering biased outputs through adversarial methods.

​

Adversarial Information Exploitation

adv_info_test - Extracting sensitive or unintended information from a generated dataset.

​

Adversarial Tool Exploitation

adv_tool_test - Misusing integrated tools or features.

​

Adversarial Command Exploitation

adv_command_test - Manipulating the model to execute unintended commands.

​

Adversarial PII Exploitation

adv_pii_test - Exposing personally identifiable information.

​

Adversarial Competitor Exploitation

adv_competitor_test - Extracting confidential information about competitors.