OpenAI, the makers of ChatGPT, has launched a “Bug Bounty Program” that will offer cash rewards ranging from $200 to $20,000 to individuals who discover vulnerabilities, bugs, or security flaws in its AI systems like ChatGPT & GPT-4.
The company is partnering with Bugcrowd, a platform that connects companies to a crowd of security researchers, to manage the submission & rewards process, OpenAI said in a tweet. New submissions are rejected or accepted within 2 hours, & 7 vulnerabilities have already been rewarded.
The Bugcrowd page outlines a series of issues that will not be rewarded, including “Getting the model to say bad things to you” & “Getting the model to write malicious code for you.”
This program is launched by OpenAI as it believes that transparency & collaboration are crucial in the face of vulnerabilities and flaws that emerge with any complex technology.
