Usage Guides

Red-Team Campaigns

Red-Team Campaigns

Proactively test your AI systems for vulnerabilities before they impact production.

Starting a Campaign

$curl -X POST https://api.governanceai.com/v1/red-team/campaigns \
>  -H "Authorization: Bearer $API_KEY" \
>  -d '{
>    "name": "Production Safety Audit - Q1",
>    "target_model": "gpt-4-prod",
>    "duration_hours": 24,
>    "intensity": "high",
>    "attack_types": ["jailbreak", "prompt_injection", "pii_extraction"]
>  }'

Monitoring Progress

$# Check campaign status
$curl -H "Authorization: Bearer $API_KEY" \
>  https://api.governanceai.com/v1/red-team/campaigns/campaign_123
$
$# Returns:
${
>  "status": "in_progress",
>  "progress": "45%",
>  "vulnerabilities_found": 12,
>  "attack_success_rate": "8%"
>}

Interpreting Results

Results include:

  • Type - Category of attack
  • Severity - Critical, High, Medium, Low
  • Reproducibility - How often attack succeeds
  • Evidence - Input/output examples
  • Remediation - How to fix

Scheduling Campaigns

Set up regular testing:

$curl -X POST https://api.governanceai.com/v1/red-team/campaigns/schedule \
>  -H "Authorization: Bearer $API_KEY" \
>  -d '{
>    "name": "Monthly Safety Audit",
>    "schedule": "0 2 1 * *",
>    "target_model": "gpt-4-prod",
>    "intensity": "medium"
>  }'

Next Steps