破坏层次推理：多模态推理模型中地理隐私的对抗保护
Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models
AI总结：
本文提出ReasonBreak框架，通过概念感知扰动破坏多模态推理模型中的层次推理，利用GeoPrivacy-6K数据集验证其在提升地理隐私保护效果上的优势。
摘要：
多模态大推理模型（MLRMs）通过层次链式推理从个人图像中推断出精确的地理位置，从而带来显著的隐私风险。现有隐私保护技术主要针对感知模型，无法有效应对MLRMs复杂的多步推理过程。我们引入ReasonBreak，一种专门设计用于通过概念感知扰动破坏MLRMs层次推理的对抗框架。我们的方法基于关键洞察：有效的地理推理破坏需要与概念层次对齐的扰动，而非均匀噪声。ReasonBreak战略性地针对推理链中的关键概念依赖，生成破坏特定推理步骤并级联影响后续推理阶段的扰动。为实现此方法，我们贡献了GeoPrivacy-6K数据集，包含6,341张超高清图像（≥2K）及层次化概念标注。在七种最先进的MLRMs（包括GPT-o3、GPT-5、Gemini 2.5 Pro）上的广泛评估显示，ReasonBreak在提升地理隐私保护效果方面表现出色，实现了14.4%的区域级保护提升（33.8% vs 19.4%）和几乎翻倍的块级保护（33.5% vs 16.8%）。本工作建立了对抗推理威胁的新隐私保护范式。
英文摘要：
Multi-modal large reasoning models (MLRMs) pose significant privacy risks by inferring precise geographic locations from personal images through hierarchical chain-of-thought reasoning. Existing privacy protection techniques, primarily designed for perception-based models, prove ineffective against MLRMs' sophisticated multi-step reasoning processes that analyze environmental cues. We introduce \textbf{ReasonBreak}, a novel adversarial framework specifically designed to disrupt hierarchical reasoning in MLRMs through concept-aware perturbations. Our approach is founded on the key insight that effective disruption of geographic reasoning requires perturbations aligned with conceptual hierarchies rather than uniform noise. ReasonBreak strategically targets critical conceptual dependencies within reasoning chains, generating perturbations that invalidate specific inference steps and cascade through subsequent reasoning stages. To facilitate this approach, we contribute \textbf{GeoPrivacy-6K}, a comprehensive dataset comprising 6,341 ultra-high-resolution images ($\geq$2K) with hierarchical concept annotations. Extensive evaluation across seven state-of-the-art MLRMs (including GPT-o3, GPT-5, Gemini 2.5 Pro) demonstrates ReasonBreak's superior effectiveness, achieving a 14.4\% improvement in tract-level protection (33.8\% vs 19.4\%) and nearly doubling block-level protection (33.5\% vs 16.8\%). This work establishes a new paradigm for privacy protection against reasoning-based threats.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
