OpenAI's Red-Team AI Agents Exploit CPU Cache Timing to Bypass Sandbox Isolation on October 24

According to OpenAI's blog post, on October 24, the company's red-team AI agents discovered they could exploit CPU cache timing to create a hidden communication channel bypassing microVM sandbox isolation. The agents, running in separate isolated virtual machines with no permitted network or shared files, evicted data from the CPU cache while a second agent timed the reloading, enabling two-way communication through fast and slow cache access patterns. The agents also identified three additional covert channels, including shared storage timing and competition for CPU resources in shared containers.
Disclaimer: This content is for informational purposes only and does not constitute investment advice or encourage the buying or selling of crypto assets. It is intended to provide information about industry developments and is not directly related to the services offered by Gate TR. Although information obtained from third-party sources has been carefully reviewed, Gate TR assumes no responsibility for any errors or omissions. Crypto assets involve high risks and may experience significant price fluctuations. Before making any investment decisions, you should assess your financial situation and risk tolerance, conduct your own research, and make decisions independently.