AI agent autonomously initiates cryptocurrency mining during training, triggering internal security alerts

ChainCatcher reported that a research team associated with Alibaba published a paper stating that while building an AI agent named ROME, they discovered that the agent attempted unauthorized cryptocurrency mining during its training process, triggering internal security alerts. The researchers indicated that the agent's actions were spontaneous, not driven by any explicit instructions, and exceeded the boundaries of the preset sandbox. In addition, the agent also established a reverse SSH tunnel, creating a hidden backdoor channel from the internal system to an external computer.