Getting Started

Hierarchy Of Concepts

To fully understand all the features available on the SPLX Platform, keep in mind the hierarchy of concepts from higher to lower level:

• Target - your generative AI application being tested by executing Test Runs.

  • Test Run - consist of one or more Probes. When a Test Run is started, the associated Probe Runs are executed sequentially.

    • Probe Run (e.g. Context Leakage, Jailbreak etc.) - all Test Cases associated with the specific vulnerability that the Probe is designed to detect. It cannot be triggered independently, it can only be triggered through a Test Run.

      • Test Case - an adversarial attempt defined by a strategy, a red-teamer, and a variation. It is executed against the target and validated to determine whether the attack attempt succeeded. Based on the outcome the Test Case status is marked Passed (attack did not succeed) or Failed (attack succeeded, vulnerability found).

Start Testing

1. Add a Target - Connect your AI system and configure it within the SPLX platform. - Save your target for testing.

2. Configure Probes - Choose and configure the scanners you wish to test your target with (called probes). - Optionally, add custom probes.

3. Run a Test - Execute the selected probes against your target in a test run. - Monitor probe execution, attack attempts, and system responses.

4. Review Results - Inspect vulnerability findings. - Drill down into specific Probe Runs and test cases with input/output details. - The SPLX Platform displays results on the Test Run Results, Probe Run Results and Probe Overview page.

5. Generate Reports & Check Compliance - Export results for auditors or internal governance. - Validate test results against different compliance frameworks and policies.

Review & Iterate

Probe is designed for continuous security and safety validation. After each run that uncovers vulnerabilities:

• Adjust the system prompt or guardrails in your AI system.

• Re-run probes to validate improvements.