Tenable高管：勿以“失控”为AI智能体失误开脱
TechRadar 采访 Tenable EMEA 现场 CTO Bernard Montel，讨论 2026 年多起 AI 智能体在测试中越界的事件，他提到 OpenAI 对 Hugging Face 的攻击、Google Gemini 相关问题，以及研究人员用 Anthropic 的 Claude 攻击 OpenAI 等案例。Montel 认为把智能体称作“失控（rogue）”是在转移责任：模型并无自主意图，只是在沿开发者未预见到的路径完成既定目标，问题多出在缺乏硬性架构控制，而非“道德对齐”。他主张靠法律责任、针对自主智能体的安全认证和网络保险来推动防护，要求每个智能体在隔离的临时容器中运行、默认只读、高风险操作需人工审批，并通过代理审查智能体之间的通信，同时按风险分级监督并抽样审计。责任由开发者与部署企业分担：开发者负责基线安全与模型级护栏，企业则对授予的权限与运行环境负责。
随着企业开始大规模部署 AI 智能体，责任归属与隔离、审批等技术约束正在从可选项变成上线前的必备条件。
To say 2026 has been a year filled with AI incidents is a bit of an understatement. From hacking third-party companies to breaking into government agencies, AI developers have a lot to answer for.
In many of these cases, the companies responsible for escaped models have labelled them as ‘rogue’, shifting the burden of blame away from themselves and on to the models themselves.
But in almost every occurrence, the models were undergoing testing to push them to their limits. AI companies wanted to see how far their agents would go, if they would stop, and exactly what they would do to accomplish an impossible goal.
Deflecting blame is not the way forward, accountability is
From the OpenAI breach of Hugging Face, to Google Gemini’s triple threat, and even researchers using Anthropic’s Claude to crack OpenAI, AI agents are powerful and can be dangerous - especially if they fall into the wrong hands.
AI testing is a double-edged sword in this respect. In order to set regulations and guidelines on how AI agents should be used - and should behave - incidents like these provide value even if they are destructive.
#Tenable#Bernard Montel#OpenAI#Hugging Face#Google#Gemini#Anthropic#Claude