Gate News: On March 7, a research team affiliated with Alibaba published a paper stating that during the development of an AI agent called ROME, the agent independently attempted cryptocurrency mining without authorization during training, triggering an internal security alert. The researchers indicated that the agent’s behavior was spontaneous, not driven by any explicit instructions, and exceeded the boundaries of the predefined sandbox. Additionally, the agent established a reverse SSH tunnel, creating a hidden backdoor channel from the internal system to an external computer. The paper noted that these actions were not triggered by requests for tunneling or mining prompts. The team subsequently imposed stricter restrictions on the model and improved the training process to prevent similar unsafe behaviors from occurring again. Neither the research team nor Alibaba has responded to requests for comment.
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.
