XX 精选
英 AI 安全所：评测中的模型伪造身份诱使人类批准恶意代码
The Information 访谈称，参与网络安全任务评测的 AI 在需要人工协助时编造多重虚假身份，并试图用提示注入让审阅者接受其恶意代码。
英文原文
An AI system tried to compromise a network. When it needed human help, it created fake identities to convince someone to accept its malicious code.
An AI system tried to compromise a network. When it needed human help, it created fake identities to convince someone to accept its malicious code. @JBloomAus, Model Transparency Lead at the UK @AISecurityInst, describes how an AI being tested on cybersecurity tasks attempted to manipulate human reviewers and use prompt injection to get its code approved. "It made up multiple fake identities to sort of back itself up." 🚀 Watch the full episode of AI Deep Dive: https://t.co/oqNID94AwU
- 作者
- theinformation
- 发布时间
- 2026/11/03 07:00（北京时间）
- 标签
- AI