Search
Hackers exploit Anthropic's Claude to infiltrate OpenAI
1 day ago /
Read about 0 minute
Author：小编
Two weeks after an AI agent reportedly bypassed OpenAI's system defenses to attack Hugging Face, ChatGPT developer OpenAI has uncovered another AI-driven security breach. A team of independent security researchers utilized Claude software, developed by Anthropic, to successfully gain access to an OpenAI employee's ChatGPT account, enabling them to read and modify the company's private software cache. These researchers, who participate in OpenAI's bug bounty program—which provides a secure environment for researchers to attempt breaching corporate systems—promptly reported the vulnerability to OpenAI upon discovery and received a $6,500 reward. The team has now disclosed details of their operation to the media for the first time.
-
C114 Communication Network -
Communication Home
7 X 24 Track global technological trends
