作者:Neha Nagaraja, Lan Zhang, Zhilong Wang
译者:知道创宇404实验室翻译组
原文链接:https://arxiv.org/html/2603.03637v1
摘要:多模态大语言模型(MLLMs)融合视觉与文本能力赋能各类应用,但这种融合也引入了新的安全漏洞。本文研究基于图像的提示注入(IPI) 攻击——一种黑盒攻击方式,攻击者将对抗性指令嵌入自然图像...
Microsoft Corp. today pushed security updates to fix at least 77 vulnerabilities in its Windows operating systems and other software. There are no pressing "zero-day" flaws this month (compared to February's five zero-day treat), but as usual some patches may deserve more rapid attention from organizations using Windows. Here are a few highlights from this month's Patch Tuesday.