Gray Swan AI
Runs large-scale red-teaming and jailbreak competitions for AI models
Is this your company?
Claim this profile to mark it as run by your company, see how many people view it, and get a badge for your website — free.
ABOUT
Gray Swan AI builds red-teaming and adversarial testing tools that stress-test AI models and agents for jailbreaks, prompt injection, and unsafe outputs. It runs public red-teaming competitions and offers an automated attack platform used by labs to harden models before release.
SIMILAR COMPANIES IN AI SAFETY
- Haize Labs
Automated red-teaming platform for finding AI model failures
- HelmGuard
AI agents that automate governance, risk and compliance
- HiddenLayer
Security platform protecting machine learning models from attacks
- Holistic AI
AI governance, risk, and compliance software for responsible AI