Google AI nga bug bounty program gilaipad, ang pag-ain-ain hangtod PHP 1.75 milyon

Google nag-lansada usa ka bag-ong programa nga adunay fokus sa pagpangita sa mga vulnerability sa ilang AI system. Kini nahigayon gamit ang blog sa Bug Hunters ni Google ug adunay mga reward nga hangtod sa USD 30,000 (~PHP 1.75 million).

Ang AI nga program alang sa bounty alang sa bug ang adunay kaugalingong fokus sa pagpangita sa mga gilangkaw sa seguridad nga espesial alang sa mga teknolohiya sa AI, sama sa ‘prompt injection’. Kini mao ang usa ka kasalutan kung ang AI makahatag sa mga panguna nga mga gawas nga mga usa.

An example of this is when Google Home unlocks a resident’s front door without notice. It could also be Google Workspace related, like summarizing a user’s emails for the use of a third party.

These incidents are classified by Google as ‘rogue actions’, which the company sees as vulnerabilities in AI harmful to security. Researchers who find security flaws in core Google products can earn from the program.

This includes platforms like Search, Gemini apps, Gmail, Drive, or Workspace. The base reward is USD 20,000, which could go as high as USD 30,000 depending on report quality.

Bugs found in other products like NotebookLM will have lower rewards. In addition, Google said having their AI models ‘hallucinate’ are incorrect outputs and aren’t eligible for rewards.

In addition, participants are encouraged to report issues with harmful or copyrighted AI-generated content through built-in feedback tools.

Here’s a table that outlines the scope of possible issues.