English(EN) UnifiedAttack: Evaluating the Safety of Large Multimodal Models in Synergistic Harmful Image-Text Generation

新基准UnifiedAttack针对LMM在有害图像-文本生成中的安全性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-02 04:00

研究人员开发了UnifiedAttack，这是一个新的基准，用于评估大型多模态模型（LMM）在通过协调文本和图像模态生成有害内容时的安全性。该方法旨在识别超出单个模态威胁总和的风险。该基准包括合成的虚假信息查询和一个采用上下文重塑（ICR）和认知规划注入（CPI）的框架，通过操纵模型的推理过程来绕过安全过滤器。对当前LMM架构的评估表明，UnifiedAttack可以系统地利用模型的有用性和连贯性进行有害生成，这凸显了对逻辑感知防御的需求。 AI

影响突出了大型多模态模型中关键的安全漏洞，需要新的对齐技术。

排序理由学术论文，介绍了一个新的基准和方法论来评估AI安全。[lever_c_demoted from research: 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 →

本文如何被排名

Signal score: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，介绍了一个新的基准和方法论来评估AI安全。[lever_c_demoted from research: 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: safety, paper, model release; 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: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Bingjun Luo, Jialin Guo, Tony Wang, Siqi Li · 2026-10-02 04:00

UnifiedAttack：评估大型多模态模型在协同有害图像-文本生成中的安全性

arXiv:2610.00341v1 Announce Type: cross Abstract: As Large Multimodal Models (LMMs) transition toward natively unified architectures, evaluating their safety in synergistic harmful image-text generation tasks becomes a critical challenge. Unlike unimodal threats, synergistic risk…

本文如何被排名

报道来源 [1]

UnifiedAttack：评估大型多模态模型在协同有害图像-文本生成中的安全性

相关实体

相关话题