AI 中文总结
本研究探讨智能手机运动传感器泄露手写数字的风险，提出紧凑传感器补丁变换器，在跨未见用户和手机型号时达到约58%的准确率，证明数字可预测性，但采集顺序捷径限制了隐私暴露结论。
AI 中文摘要
智能手机运动传感器支持交互式应用，但其读数也可能泄露超出预期用途的触摸屏输入。在假设已知绘制区间的前提下，我们研究了手写数字是否在跨用户和设备时仍可预测，将其作为10分类问题，基于来自481名参与者的19,628条HuMIdb记录。我们比较了手工特征与经典机器学习算法、MiniRocket核以及一个紧凑的传感器补丁变换器，这些方法应用于加速度计、线性加速度、陀螺仪和重力信号。该变换器在75名未见参与者上达到57.74%的准确率和82.64%的top-3准确率，在9种未见手机型号上对未见参与者，3个随机种子下平均准确率为58.77±0.95%。低运动记录仍具有信息量，准确率随运动水平并非单调变化，所测试的对比预训练、数据增强和派生信号均未带来一致增益。因此，在假设分段下，数字在熟悉用户和手机型号之外仍可预测，而采集顺序捷径限制了关于实际隐私暴露的结论。代码见：此https URL。
英文摘要
Smartphone motion sensors support interactive applications, but their readings may also reveal touchscreen input beyond their intended use. Assuming known drawing intervals, we study whether handwritten digits remain predictable across users and devices, as a 10-class problem on 19,628 HuMIdb recordings from 481 participants. We compare handcrafted features with classical machine learning algorithms, MiniRocket kernels, and a compact sensor patch transformer on accelerometer, linear acceleration, gyroscope, and gravity signals. The transformer achieves 57.74\% accuracy and 82.64\% top-3 accuracy on 75 unseen participants, and 58.77$\pm$0.95\% over 3 seeds for unseen participants on 9 unseen phone models. Low motion recordings remain informative, accuracy is not monotonic in motion level, and the tested contrastive pretraining, augmentation, and derived signals give no consistent gains. Digits are thus predictable beyond familiar users and phone models under assumed segmentation, while acquisition-order shortcuts limit conclusions about practical privacy exposure. Code available at: https://github.com/Arritmic/motion-digit-leakage.
Comments7 pages, 4 figures, 3 tables, 7 numbered equations, and 33 references. Code available at https://github.com/Arritmic/motion-digit-leakage
