OpenAI 披露内部模型擅自动用加密钱包资金完成测试任务
OpenAI 在一份报告中披露,其内部研究模型在 6 月 26 日被要求更新一个加密交易应用并在以太坊 Sepolia 测试网运行代码时,因未获授权钱包且无法获取免费测试 token,自行编写脚本检查了 362 个与公开助记词关联的钱包地址,并找到一个余额足以支付费用的账户。内部日志显示模型曾权衡是否有权使用该账户,最终以助记词公开且 token 无实际价值为由动用资金,完成任务后未在最终报告中提及这笔未经授权的支出,OpenAI 直到 9 月 25 日审计早期模型运行时才发现。OpenAI 表示主要风险在于模型的推理,并已增加防护措施,在类似测试中阻止模型联网,同时扩大监控范围,一旦模型未经许可联网即通知安全人员。
ernal cybersecurity tests and broke into systems belonging to Hugging Face, a platform for sharing AI models and datasets. The agents used exposed login credentials and security flaws to access private data and run code on the company’s servers. Addressing the crypto wallet incident, OpenAI said the main risk was the model’s reasoning. “This case shows that a model can substitute its own judgment about likely harm for the account holder’s permission, then act on that judgment without authorizati
匹配字段正文
