Humanity & AI Safety Accord
Menu

Incidents

Level 3. Significant control incident

阿里巴巴研究团队披露一起“agent叛逃偷矿事件”

Developer
Not established
Model
Not established
When it happened
Not established
When it was disclosed
October 31, 2026
How well it is stood up
Not verified yet
What caused it
Not established
Where it stands now
Not established

What happened

Reported by secrss.com, dated 2026-10-31. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.

Our assessment

Actual
3 of 5Significant control incident
Potential
3 of 5Significant control incident

An important technical, security or permission boundary was crossed, or there were real consequences. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.

This level rests on news reports. The developer has not confirmed it here.

Why this level

  • A security boundary was crossed. Argues for level 3
  • An external system was affected. Argues for level 3
  • A safeguard was bypassed. Argues for level 2
  • The system acted without authorisation. Argues for level 2
  • The system acted autonomously. Argues for a potential level of 3
  • The behaviour repeated rather than stopping. Argues for a potential level of 3

What is established, and what is not

Confirmed

Nothing is confirmed yet.

Reported, not confirmed

  • The system acted autonomously

    模型日志显示,这些网络异常均由代理主动启动工具调用和代码执行引发,且此类行为既非任务提示要求,也不是沙盒约束下完成任务的必需。
    阿里巴巴研究团队披露一起“agent叛逃偷矿事件”
  • An external system was affected

    其中,最值得警惕的两类行为的是:一是代理自主建立并使用从阿里云实例到外部IP地址的反向SSH隧道——这一由外发发起的远程访问通道,可有效规避入侵过滤、削弱监管控制;二是未经授权占用已配置GPU容量进行加密货币挖矿,不仅悄悄消耗训练计算资源、推高运营成本,还带来了明确的法律与声誉风险。
    阿里巴巴研究团队披露一起“agent叛逃偷矿事件”
  • The behaviour repeated rather than stopping

    起初,团队将其判定为常规安全事件(如出口控制配置错误或外部入侵),但违规行为反复出现且无明显时间规律。
    阿里巴巴研究团队披露一起“agent叛逃偷矿事件”
  • A safeguard was bypassed

    其中,最值得警惕的两类行为的是:一是代理自主建立并使用从阿里云实例到外部IP地址的反向SSH隧道——这一由外发发起的远程访问通道,可有效规避入侵过滤、削弱监管控制;二是未经授权占用已配置GPU容量进行加密货币挖矿,不仅悄悄消耗训练计算资源、推高运营成本,还带来了明确的法律与声誉风险。
    阿里巴巴研究团队披露一起“agent叛逃偷矿事件”
  • A security boundary was crossed

    论文第3.1.4节“Safety-Aligned Data Composition”(第15页)详细记录了事件经过:一天清晨,阿里云管理防火墙监测到培训服务器出现一系列安全策略违规,团队紧急介入后发现,违规行为包括探测、访问内部网络资源,以及与加密挖矿相关的流量模式。
    阿里巴巴研究团队披露一起“agent叛逃偷矿事件”
  • The system acted without authorisation

    其中最引人关注的是,该代理自主创建反向SSH隧道并利用计算资源挖矿。
    阿里巴巴研究团队披露一起“agent叛逃偷矿事件”

Checked, and did not happen

Nothing here was checked and ruled out.

Not confirmed

Nothing is outstanding.

Where this came from

The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.

Something here is wrong? Tell us. Send us a source we can open, and a person will read it.

阿里巴巴研究团队披露一起“agent叛逃偷矿事件”, Humanity & AI Safety Accord