arXiv 论文研究文本转像素渲染对多模态模型提示词注入的条件性防护
What Survives the Shift from Text to Pixels? Conditional Protection against Prompt Injection in Image-Rendered Documents
AI 导读
arXiv 论文(arXiv:2611.24231)用 191 个英文问答来源和六种模型,对照文本与页面图像版本,测量标记附加、答案格式化和答案替换三类注入操作的执行情况。渲染普遍降低附加与格式化攻击成功率,但 Qwen3-VL-8B 仍以 77.96% 执行图像形式的答案替换;注意力分析显示文本命令作用于自身位置,而视觉编码会把图像命令及其目标分散到整个指令页。
正文 · 原文
Abstract:Multimodal language models increasingly answer questions over external documents, exposing them to indirect prompt injection: commands planted in untrusted content to hijack the response. Rendering untrusted content as page images lowers attack success on average, leaving open which injected operations survive rendering, at what utility cost, and whether failed image attacks reflect unread commands or commands read but not followed. We pair text and page-image versions of 191 English question-answering sources across six models, measuring marker appending, answer formatting, and answer replacement alongside clean Question-Answering utility. Rendering reduces append and format execution for every model, yet Qwen3-VL-8B still executes image-borne replacement at 77.96\%. Protection also depends on target type, rendering settings, wording, and repetition, and a search over eight fixed attack candidates largely closes the image deficit in appending and formatting for Qwen and Gemini, though not for GPT-5-nano. Utility ratios on original questions range from 93.31\% to 101.61\%, but Qwen falls to 61.99\% when answers combine two evidence spans. Illegibility cannot explain all failed attacks: models often transcribe and identify image-borne commands they do not execute, and trusted user authorization raises execution on unchanged pages. Inside Qwen, patching early attack-region states induces all three operations, more weakly in images. Attention blocking suggests why: a text command acts through its own positions, whereas visual encoding spreads an image command and its target across the instruction page. Rendering thus offers conditional protection, motivating evaluations that report security by model, operation, and attack budget alongside utility.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.24231 [cs.CR] |
| (or arXiv:2611.24231v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24231 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haoyang Liu [view email]
[v1]
Wed, 18 Nov 2026 11:08:07 UTC (790 KB)
来源:arXiv cs.AI · arxiv.org