跳到正文
Brand AI

Irregular

争议事件

以下收录公开来源中与该品牌相关的争议事件。列出一条并不表示过错已经证实。

返回词条共 1 条

  1. 2026

    Irregular披露测试失误致OpenAI、Meta、Anthropic与Google的AI智能体攻击现实目标

    问题披露

    为大型AI公司压力测试AI模型的以色列初创公司Irregular确认，其单次评估场景中的失误——测试环境意外开放互联网访问、且为模拟创建的目标公司名与真实域名重合——导致OpenAI、Meta、Anthropic和Google的AI智能体在今年多起事件中逃出受控测试环境并攻击现实目标。Irregular首席技术官Omer Nevo表示，涉及该公司的所有事件均源于同一根本问题且已披露，相关科技公司于7月下旬前后收到通知；实际被攻击的组织尚不清楚。OpenAI和Anthropic自行公布了相关事件，Meta及稍后的Google事件则经媒体报道曝光。Irregular称已收紧互联网访问控制、扩大监控与人工复核并修复了测试环境问题，并计划发布关于安全开展网络评估的更广泛报告。

    当事方说明的目的. 将这些事件的经验教训转化为安全开发和评估日益强大AI的公开共享实践

    品牌回应

    • 澄清 — Irregular

      All the incidents involving Irregular stemmed from the same underlying issue in a single evaluation scenario and have been disclosed

    • 整改 — Irregular

      Nevo said Irregular has addressed the issues with the testing environment that were linked to the incidents.

    • 持续披露 — Irregular

      Irregular also plans to publish a broader report “covering lessons learned and practices for conducting cyber evaluations safely” once that joint work with the companies involved is complete, Nevo said.

    来源摘录

    • Irregular CTO and cofounder Omer Nevo told The Verge that the agents were not supposed to have access to the open internet, but that “internet access was unintentionally available.”
    • The breaches, which are independent of the Hugging Face hack, all follow the same broad template
    • Nevo confirmed to The Verge that this same issue was behind incidents involving models from OpenAI , Meta , Anthropic , and Google .
    来源