A Fundamental Flaw Leaves LLMs Strikingly Vulnerable To Attack

> 一个根本性缺陷使大语言模型极易受到攻击

来源: technologyreview.com | 主题: AI | 评论: 38

时间: on Thursday July 30, 2026 @06:00PM

joshuark quotes a report from MIT Technology Review: It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a team of researchers argue in a paper presented at the International Conference on Machine Learning, a top AI conference, this month.

⋯ 继续阅读请开通会员 ⋯