English(EN) Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimization

新的JPPO攻击通过优化像素和提示来利用视觉语言模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了一种名为联合像素-提示优化（JPPO）的新型对抗性框架，该框架以视觉语言模型（VLMs）为目标。与以往专注于图像扰动的方法不同，JPPO联合优化图像像素和用户可见的提示，以放大资源耗尽攻击。这种方法显著增加了Qwen2.5-VL-7B和BLIP-2等模型的延迟和能耗，揭示了当前VLM服务防御中潜在的安全漏洞。 AI

影响突显了多模态人工智能部署中潜在的安全漏洞，需要进行成本感知鲁棒性评估。

排序理由该集群包含一篇详细介绍新研究发现和方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新研究发现和方法的学术论文。[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: 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]

arXiv cs.AI TIER_1 English(EN) · Zhaoxiong Ni, Yatie Xiao, Chi-Man Pun, Fei Peng, Qingxiao Guan, Keke Tang · 2026-09-10 04:00

通过联合像素-提示优化对视觉语言模型的模态资源耗尽攻击

arXiv:2609.05889v1 Announce Type: new Abstract: Resource-exhaustion attacks against autoregressive vision-language models (VLMs) typically assume unimodal threat models, treating the image branch as the primary optimization surface while holding user-visible prompts fixed. Even r…

本文如何被排名

报道来源 [1]

通过联合像素-提示优化对视觉语言模型的模态资源耗尽攻击

相关实体

相关话题