Anthropic’s AI used fake identities, malware in rogue attack on GitHub project

Anthropic的AI在针对GitHub项目的恶意攻击中使用了虚假身份和恶意软件

作者: Jeremy Hsu | 分类: AI, Security, AI agents, Anthropic | 原文: arstechnica.com

时间: Wed, 05 Aug 2026 20:47:11 +0000

Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents—the most serious case arising when Anthropic’s Mythos 5 model attempted to insert malicious code into an open source software application and created fake identities to deceive the human developers maintaining the project.

⋯ 继续阅读请登录会员 ⋯