Open AI has announced a bug bounty program for ChatGPT to reward people who report any security flaws, vulnerabilities, or other issues within the AI system. The rewards will range from $200 for low-severity findings to $20,000 for exceptional discoveries. “OpenAI’s mission is to create artificial intelligence systems that benefit everyone. To that end, we invest heavily in research and engineering to ensure our AI systems are safe and secure,” said the company in a blog post.
Submission for the Bug Bounty Program for ChatGPT
The company has partnered with a leading bug bounty platform, Bugcrowd, to manage the submission and reward process, which is designed to ensure a streamlined experience for all participants. According to the program’s page, the participants are bound to keep the vulnerability details confidential until authorized for release by OpenAI’s security team, which aims to provide authorization within 90 days of report receipt.
Moreover, the bounty excludes rewards for jailbreaking ChatGPT or causing it to generate malicious code or text. “Issues related to the content of model prompts and responses are strictly out of scope, and will not be rewarded,” reads a warning on the Bugcrowd’s page. OpenAI said that this program is a way for the company to recognize and reward the valuable insights of security researchers who contribute to keeping its technology and company secure.
Problems with ChatGPT
Previously, ChatGPT dealt with a lot of bugs when users started complaining about their private chats being leaked. Users also reported seeing names of conversations they weren’t a part of. Later, a Twitter user posted that they had found more than 80 secret plugins while hacking ChatGPT.
Also read: ChatGPT to Face World’s First Defamation Lawsuit in Australia
