OpenAI begins bug bounty program for ChatGPT

The company behind ChatGPT has partnered with Bugcrowd, a crowdsourcing cybersecurity platform to manage submissions and rewards. (Illustration by Suneesh Kalarickal)

OpenAI has announced a bug bounty program with cash rewards from $200 to $20,000 for security vulnerabilities disclosed.

The company behind ChatGPT has partnered with Bugcrowd, a crowdsourcing cybersecurity platform to manage submissions and rewards.

"Our rewards range from $200 for low-severity findings to up to $20,000 for exceptional discoveries," said OpenAI in a post on their website.

"We invite you to report vulnerabilities, bugs, or security flaws you discover in our systems. By sharing your findings, you will play a crucial role in making our technology safer for everyone."

The one exception are any bugs found within the model by deliberately jailbreaking it or forcing it to give inaccurate answers.

OpenAI says, "Model safety issues do not fit well within a bug bounty program, as they are not individual, discrete bugs that can be directly fixed. Addressing these issues often involves substantial research and a broader approach."

Also out of the scope of the program, are any bugs or issues related to Model Hallucinations, i.e. the AI model wrongly assuming the validity of a statement.

"Issues related to the content of model prompts and responses are strictly out of scope, and will not be rewarded unless they have an additional directly verifiable security impact on an in-scope service," wrote OpenAI in the post.