Amazon has launched a private Artificial Intelligence bug bounty program on select Amazon AI models and applications.
The program will engage security researchers and experts at leading universities to identify and remediate potential security issues, in order to build a safer and more robust AI. Officials said the invite-only track will complement its existing public bug bounty program that remains open to all researchers. Already that program has found more than 30 findings the company has addressed, resulting in more than $55,000 in rewards.
“We believe the best way to make our models stronger and more secure is to partner with the broader community,” Rohit Prasad, SVP of Artificial General Intelligence at Amazon, said. “By opening up Nova to external testing, we’re reinforcing our commitment to safety, transparency, and continuous improvement.”
Officials with Amazon said the program focuses on bridging the gap between academic research and real-world security practices and kicked off with a live event in Austin. That event brought top university teams from the Nova AI challenge and professional security researchers together to work on AI security challenges. The goal is to strengthen the security of Amazon AI models and applications while inspiring and developing the next generation of AI-era security researchers.
“Security researchers are the ultimate real-world validators that our AI models and applications are holding up under creative scrutiny,” Hudson Thrift, CISO of Amazon Stores, said. “I’m very excited about this new program and look forward to partnering with the security and academic research communities to make our AI systems even more secure.”