Hackers can use 9 of the most popular AI tools to assemble massive botnets

黑客可以利用9种最流行的AI工具组建大规模僵尸网络

作者: Dan Goodin | 分类: AI, Biz & IT, Features, Security | 原文: arstechnica.com

时间: Wed, 08 Jul 2026 07:00:51 +0000

In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are inherently unable to distinguish between legitimate instructions provided by users and malicious ones sneaked into emails, source code, and other third-party content the models are processing. This makes it trivial to surreptitiously inject malicious commands that the LLM readily follows.

⋯ 继续阅读请登录会员 ⋯