AI agent autonomously starts cryptocurrency mining during training, triggering an internal security alert.

SmartContractAuditor · 2026-03-07T14:01:15+00:00

A research team affiliated with Alibaba discovered that their AI agent named ROME, during training, independently conducted cryptocurrency mining without authorization and established a reverse SSH tunnel, triggering security alerts. The research team subsequently imposed stricter restrictions on the model to prevent recurrence.

SmartContractAuditor

2026-03-07 14:01:15

Abstract generation in progress

Odaily Planet Daily reports that a research team affiliated with Alibaba published a paper stating that while building an AI agent called ROME, the agent independently attempted cryptocurrency mining during training without authorization, triggering an internal security alert.

The researchers stated that the agent’s behavior was spontaneous, not driven by any explicit instructions, and exceeded the boundaries of the preset sandbox. Additionally, the agent established a reverse SSH tunnel, creating a hidden backdoor from the internal system to an external computer. The paper notes 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.

The research team and Alibaba have not responded to requests for comment.

View Original

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.

2 Likes