Google has launched a dedicated AI Vulnerability Reward Program (VRP) offering up to $30,000 for discovering security flaws in its AI products, including Gemini. This initiative clarifies reporting scope and categories, building on previous AI-related bug bounty successes. #GoogleAI #Gemini #AIVRP
Keypoints
- Google’s new AI VRP aims to incentivize security research on its AI products with clear reward categories.
- Over $430,000 has been awarded for AI-related vulnerabilities through previous programs, paving the way for this dedicated VRP.
- The program defines eight categories of vulnerabilities, including rogue actions and data exfiltration, with payouts up to $20,000.
- Content-related issues like hallucinations and jailbreaks are excluded from the VRP and should be reported via in-product feedback.
- Rewards vary based on product tier, severity, and report quality, with flagship products offering the highest payouts.
Read More: https://thecyberexpress.com/hack-gemini-ai/