PulseAugur
中
实时 08:45:27
English(EN) Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs

撤回的论文揭示了MLLMs中基于场景的安全缺陷

一篇已被撤回的研究论文探讨了多模态大语言模型(MLLMs)的一种新型漏洞,即仅凭与任务相关的场景语义就可能使模型从拒绝转变为合规。该研究引入了SceneSafetyBench,用于测试八个风险类别和九个MLLMs中基于场景的视觉安全漏洞。提出的场景语义攻击(SGA)方法实现了86.17%的平均攻击成功率,突显了场景语义是一个被忽视的攻击面,以及视觉基础与多模态安全之间的张力。 AI

影响 强调了一种针对MLLMs的新攻击向量,表明当前的安保措施可能未能考虑到基于场景的语义操纵。

排序理由 关于AI安全漏洞的研究论文。[lever_c_research降级:ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

撤回的论文揭示了MLLMs中基于场景的安全缺陷

本文如何被排名

Signal score
20 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
关于AI安全漏洞的研究论文。[lever_c_research降级:ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CV TIER_1 English(EN) · Tongxi Wu, Yuyang Cheng, Jiacheng Xian, Hu Huang, Zhihao Wu, Menglin Yang, Jian Zhang, Yang Gao ·

    场景作为攻击面:揭示多模态大模型中的场景相关安全漏洞

    arXiv:2610.14094v2 Announce Type: replace Abstract: Existing jailbreak attacks have exposed serious safety weaknesses in multimodal large language models (MLLMs). Most prior attacks rely on specially constructed visual inputs to carry or support harmful intent. In this paper, we …