发表机构
Purdue University; Indiana University School of Medicine（普渡大学; 印第安纳大学医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出AutoLocate框架，利用点图渲染中的抗锯齿伪影，通过黑盒优化实现高精度位置恢复，平均误差低至1米，比现有方法精确200倍以上，并提供了缓解策略和风险评估工具。
AI 中文摘要
点图将个体数据点以点的形式可视化在地理区域上，广泛应用于各个领域，以表示敏感数据中的空间模式。然而，对于点图相关隐私风险的理解仍然有限，尤其是对于覆盖大地理区域的地图。在本文中，我们系统性地分析了这些风险，并提出了AutoLocate，一个用于高精度位置恢复的自动化框架。AutoLocate的核心在于利用地图渲染过程中引入的抗锯齿伪影，这些伪影无意中编码了关于点位置的亚像素信息。AutoLocate将位置恢复问题表述为一个黑盒优化问题，通过最小化目标地图与渲染候选地图之间在这些伪影上的感知差异，迭代地细化估计坐标。在真实世界和合成数据集上，针对不同的攻击场景和广泛的地图配置（如地图比例尺、背景、分辨率）进行的大量实验，证明了AutoLocate的有效性。特别是，在美国小比例尺地图上，它实现了平均恢复误差低至1米（约0.0002像素精度），比现有方法精确200倍以上。我们还提出了缓解策略，并引入了一个隐私风险评估工具，以帮助从业者在发布点图时评估和减少隐私泄露。
英文摘要
Dot maps, which visualize individual data points as dots over a geographic region, are widely used across diverse domains to represent spatial patterns in sensitive data. However, the understanding of the privacy risks associated with dot maps remains limited, particularly for maps covering large geographic areas. In this paper, we systematically analyze these risks and present AutoLocate, an automated framework for high-precision location recovery. At its core, AutoLocate exploits anti-aliasing artifacts introduced during map rendering, which inadvertently encode sub-pixel information about dot locations. AutoLocate formulates location recovery as a black-box optimization problem, iteratively refining estimated coordinates by minimizing perceptual discrepancies over these artifacts between the target map and rendered candidate maps. Extensive experiments on both real-world and synthetic datasets, across different attack scenarios and a broad range of map configurations (e.g., map scale, background, resolution), demonstrate the effectiveness of AutoLocate. In particular, it achieves average recovery errors as low as 1 meter (approximately 0.0002 pixel precision) on small-scale maps of the United States, over 200x more accurate than existing approaches. We also propose mitigation strategies and introduce a privacy risk assessment tool to help practitioners evaluate and reduce privacy leakage when publishing dot maps.
CommentsAccepted to the ACM Conference on Computer and Communications Security (CCS), 2026. Code is available at: https://github.com/PuddlesPenguin/AutoLocate/
