Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
物理约束数字孪生在城市行人流传感器完整性中的应用：利用共形保证检测隐蔽虚假数据注入
Abstract: City pedestrian counting systems now feed economic indicators, planning decisions and safety operations, yet the twins built on top of them treat the incoming stream as ground truth. We study what happens when it is not. 摘要： 城市行人计数系统目前为经济指标、规划决策和安全运营提供数据支持，然而建立在这些系统之上的数字孪生模型却将输入的数据流视为“地面真值”（Ground Truth）。我们研究了当这些数据并非真实可靠时会发生什么。
We formalise stealthy false data injection for city-scale pedestrian sensing, where the map from latent flow to observation is far more rank deficient than in the power and water networks for which stealth has been characterised. 我们对城市规模行人感知中的隐蔽虚假数据注入进行了形式化定义。在这种场景下，从潜在流量到观测值的映射比电力和水网系统中的映射具有更高的秩亏损（Rank Deficient），而隐蔽性攻击在电力和水网系统中已有明确特征。
Our twin estimates directed flows on the pedestrian street graph, assimilates counts through a learned graph-localised gain, and is trained against a flow conservation residual that couples metered and unmetered segments. 我们的数字孪生模型通过行人街道图估算定向流量，利用学习到的图局部增益（Graph-localised gain）同化计数数据，并针对耦合了已监测和未监测路段的流量守恒残差进行训练。
Detection combines the innovation with that residual, and the alarm threshold is set by adaptive conformal calibration rather than by hand. 检测过程将创新（Innovation）与该残差相结合，并通过自适应共形校准（Adaptive Conformal Calibration）而非人工设定来确定报警阈值。
To measure what the physics buys, we define the attack margin, the relative reduction in worst-case corruption of the estimated flow field, achieved against a white-box adversary that optimises directly through the twin. 为了衡量物理约束带来的收益，我们定义了“攻击裕度”（Attack Margin），即在面对通过数字孪生直接进行优化的白盒攻击者时，估计流场在最坏情况下的损坏程度的相对减少量。
On six years of Melbourne data the margin reaches 0.54 against a single compromised device and falls to 0.19 when a third of the fleet is compromised, on a network where only 1.18 per cent of walkable segments are metered. 基于墨尔本六年的数据，在仅有 1.18% 的可步行路段设有监测点的情况下，当单个设备被入侵时，攻击裕度达到 0.54；当三分之一的设备被入侵时，该数值降至 0.19。
Replacing the street graph by a distance graph collapses it to 0.09, which shows that the gain comes from the conservation law rather than from locality. 将街道图替换为距离图后，该数值降至 0.09，这表明性能增益源于物理守恒定律，而非单纯的地理局部性。