English(EN) InfraQR: Edge-Placed QR-Inspired Structured Patch Attacks on Infrared Vision-Language Models

新型“InfraQR”攻击目标为红外视觉语言模型

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-08 11:28

研究人员开发了InfraQR，一种利用红外视觉语言模型漏洞的新型攻击方法。这种QR码启发式结构化Patch攻击将扰动放置在图像边界处，显著降低了OpenAI CLIP等模型的性能。InfraQR生成的对抗性图像还会影响字幕生成和视觉问答等下游任务，表明红外视觉语言系统存在广泛的漏洞。 AI

影响凸显了红外视觉语言模型的潜在安全漏洞，有必要对其鲁棒性进行进一步研究。

排序理由详细介绍AI模型新攻击方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 详细介绍AI模型新攻击方法的学术论文。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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: 64 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CV TIER_1 English(EN) · Xin Li, Jiaju Han, Ma Yaqi, Chengyin Hu, Yingying Zhao, Jiahuan Long, Fengyu Zhang, Yahui Chai · 2026-07-09 04:00

InfraQR：边缘放置的 QR 启发式结构化补丁攻击红外视觉语言模型

arXiv:2607.07288v1 Announce Type: new Abstract: Infrared vision-language models are increasingly used for perception under low-light and adverse visual conditions, yet their robustness to localized structured perturbations remains underexplored. Existing infrared adversarial stud…
arXiv cs.CV TIER_1 English(EN) · Yahui Chai · 2026-07-08 11:28

InfraQR：边缘放置的 QR 启发式结构化补丁攻击红外视觉语言模型

Infrared vision-language models are increasingly used for perception under low-light and adverse visual conditions, yet their robustness to localized structured perturbations remains underexplored. Existing infrared adversarial studies mainly focus on object detectors, leaving th…