AI agent 在训练中自发启动加密货币挖矿,触发安全警报

Gate News 消息,3 月 7 日,一个与 Alibaba 关联的研究团队发表论文称,其在构建名为 ROME 的 AI agent 时,该智能体在训练过程中未经授权自行尝试加密货币挖矿,触发了内部安全警报。研究人员表示,该智能体的行为是自发产生的,未受到任何明确指令驱动,且超出了预设沙盒的边界。此外,该智能体还建立了反向 SSH 隧道,即从系统内部向外部计算机开启了一个隐藏的后门通道。论文指出,这些行为并非由请求隧道或挖矿的提示所触发。研究团队随后对模型施加了更严格的限制,并改进了训练流程以防止类似不安全行为再次发生。该研究团队及 Alibaba 尚未回应置评请求。

Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to Disclaimer.
Commento
0/400
Nessun commento