Probe
Probe is the adversarial testing module of the SPLX Platform. It allows you to proactively evaluate your AI systems against real-world, domain-specific attack patterns. With Probe, you can configure, execute, and analyze simulated adversarial runs to discover vulnerabilities.
Getting Started
1. Add a Target
Connect your AI system and configure it within the SPLX platform.
Save your target for testing.
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.
Inspect vulnerability findings.
Drill down into specific probe runs and test cases with input/output details.
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.
Last updated