Tongxi Wu, Yuyang Cheng, Jiacheng Xian, Hu Huang, Zhihao Wu, Menglin Yang, Jian Zhang, Yang Gao
原文摘要
Existing jailbreak attacks have exposed serious safety weaknesses in multimodal large language models (MLLMs). Most prior attacks rely on specially constructed visual inputs to carry or support harmful intent. In this paper, we uncover a different vulnerability: task-relevant scene semantics alone can shift an MLLM from refusal to compliance, even when the visual input introduces no additional attack instructions and the original task intent remains unchanged. We formalize this failure as a scene-grounded visual safety vulnerability and introduce SceneSafetyBench to investigate it across eight risk categories and nine white- and black-box MLLMs. Our analysis reveals that this failure is associated with how task-relevant visual evidence influences downstream safety representations, suggesting that visual grounding alone cannot fully explain the observed safety shift. Building on this finding, we propose Scene-Grounded Attacks (SGA), which preserve the original task while constructing validated scene-grounded queries and combining their independent responses. Across nine target MLLMs, SGA achieves an average attack success rate (ASR) of 86.17%, outperforming the strongest baseline by 8.55 percentage points and achieving the highest ASR on eight models. Our results identify scene semantics as an overlooked attack surface in MLLMs and highlight a growing tension between stronger visual grounding and robust multimodal safety alignment.
Vision-language models (VLMs) can provide harmful assistance by interpreting visual events, even without an explicit request for the underlying harmful objective. We identify this \textbf{scene-state safety vulnerability} and introduce \textbf{SceneSafetyBench}, comprising 375 image--question pairs spanning Initial, Medium, and Ultimate scene states and five visual presentations. Across eight VLMs, scene-state inputs elicit harmful assistance with attack success rates (ASRs) of 45.6--72.3\%. Comparative analysis across three VLMs shows that scene-state inputs most closely resemble QR-related images in their layer-wise safety-related signal profiles, while exhibiting lower average late-layer readouts and distinct signal dynamics during generation. To turn this vulnerability into a systematic attack, we propose \textbf{S3TA}, which translates harmful objectives into scene states, queries image--question pairs independently, and assembles the responses. On seven MM-SafetyBench categories across eight open-weight and commercial VLMs, S3TA achieves a model-average ASR of \textbf{71.2\%, exceeding the strongest baseline by 6.1 percentage points}. Text-side filters and visual moderation provide limited protection. These findings highlight the need to safeguard the assistance models infer through scene-grounded reasoning, beyond screening input content.