Google has launched a new Bug Bounty Program to find issues in its AI systems. The company will pay up to $30,000 (around Rs. 26 lakh) to people who find serious security issues in AI tools like Gemini, Bard, Gmail, and Google Workspace.
The tech giant’s focus is on “rogue actions.” These happen when an AI is tricked into doing something it should not. For example, AI could be made to unlock smart home devices or send private email data without permission.
Not all AI mistakes will fetch rewards for bounty hunters. Only issues that affect security, data, or safety will be considered. Simple errors or wrong answers from AI can be reported through regular feedback tools.
Google has announced rewards of up to $20,000 for big bugs in important products like Google Search, Gemini Apps, Gmail, and Drive. With additional bonuses for high-quality or novel reports, the total reward can reach up to $30,000. Smaller rewards are also available for minor issues in other tools like NotebookLM or Jules.
The tech firm launched the AI Vulnerability Reward Program (AI VRP) in October of 2023 and has already compensated researchers with a sum in excess of $430,000 for the identification of AI vulnerabilities. This shows the company's intention to protect its AI ecosystem on a preventative schedule.
Google also introduced CodeMender, an AI tool that helps fix security problems in software automatically. It has already helped fix 72 problems in open-source software after being checked by experts.
The bounty program is open to everyone. Security researchers, ethical hackers, and AI developers worldwide can submit bugs through Google’s Bug Hunters platform. Reports must follow the company’s rules to qualify for rewards.
This program shows that Google is truly serious about AI safety. By interacting with experts worldwide, Google is committed to making sure that its AI tools are safe, secure, and trustworthy to be used by all.
Also Read – Supreme Court Allows Google Play App Store Changes to Proceed