测试多语言视觉模型在流程图攻击下的安全漏洞。
MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models
- 用五种语言的流程图编码恶意指令，评估模型漏洞。
- 拉丁语系语言攻击成功率高，非拉丁语系显著降低。
- 揭示当前安全机制无法跨语言通用，适合安全研究者参考。
视觉-语言模型（VLMs）在多模态任务中表现强劲，但其安全性仍面临挑战。以往研究发现，结构化视觉提示如流程图可有效绕过VLM的安全限制，但多数工作局限于英语环境。本文提出MLingualFC，一个用于评估多语言VLM安全漏洞的多模态基准，采用流程图图像形式，在印地语、旁遮普语、西班牙语、罗马尼亚语和德语五种语言中编码有害指令。我们在黑盒威胁模型下评估了Qwen2.5-VL、Gemma-4和Pangea等主流多语言VLM。结果显示显著的多语言安全差距：拉丁字母语言攻击成功率（ASR）较高，表明视觉内容编码能有效绕过跨语言对齐；而非拉丁字母语言（如旁遮普语）的ASR明显更低，暗示问题更可能源于视觉文本识别能力而非安全对齐强度。这表明当前VLM安全机制无法跨语言与模态泛化。相关资源见https://github.com/Rishabhpm23/MLingualFC。
原文摘要 · Abstract (English)
Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge. While prior work has shown that structured visual prompts such as flowcharts can effectively jailbreak VLMs, existing studies are largely limited to English-centric settings. In this paper, we introduce MLingualFC, a multilingual multimodal benchmark designed to evaluate jailbreak vulnerabilities of VLMs across diverse languages using structured flowchart representations. MLingualFC encodes harmful instructions into flowchart images across five languages (Hindi, Punjabi, Spanish, Romanian, and German). We evaluate state-of-the-art multilingual VLMs, including Qwen2.5-VL, Gemma-4, and Pangea, under a black-box threat model. Our results reveal significant multilingual safety gaps. Flowchart-based attacks achieve high attack success rates (ASR) in case of Latin script languages, demonstrating that visual encoding of harmful content effectively bypasses safety alignment across languages. In contrast, non-Latin script languages such as Punjabi exhibit substantially lower ASR, suggesting potential limitations in visual text recognition rather than stronger safety alignment. These findings highlight that current VLM safety mechanisms fail to generalize across languages and modalities. Resources are available at https://github.com/Rishabhpm23/MLingualFC
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。