arXiv cs.CY· Rameen Mahmood, Omar El Shahawy, Souptik Barua, Zachary Beattie, Jeffrey Kaye, Xuhai "Orson'' Xu, Chao-Yi Wu, Danny Yuxing Huang·· 10 天前AI 评分28
将加密网络流量解读为纵向行为信号：基于 Transformer 与稀疏自编码器的睡眠、压力与孤独感被动感知
From Packets to Patterns: Interpreting Encrypted Network Traffic as Longitudinal Behavioral Signals
AI 导读
研究用带 per-user adapter 的 Transformer 加稀疏自编码器，从加密手机网络流量中提取可解释行为特征，并与睡眠障碍、压力、孤独感关联。结果显示三者时间结构不同：压力主要对应稳定的个体间差异，孤独感对应个体内变化，睡眠障碍则两者兼有；这些个体内动态无法被预定义流量特征捕捉。
正文 · 原文
Abstract:Human behavior is difficult to observe continuously at scale, yet it leaves measurable traces in everyday device use. We test whether encrypted smartphone network traffic---a ubiquitous, always-on, passive sensing modality---can passively capture behavioral patterns related to sleep, stress, and loneliness. We model shared behavioral structure using a transformer backbone with per-user adapters, allowing the model to represent both typical individual behavior and deviations from it. To make these representations interpretable, we apply a sparse autoencoder to extract behavioral features corresponding to distinct patterns of activity. We relate these features to sleep disturbance, stress, and loneliness using generalized estimating equations with Mundlak decomposition, separating between-person differences from within-person changes over time. We find that the three outcomes reflect distinct temporal structures: stress is primarily associated with stable between-person differences, loneliness with within-person variation, and sleep disturbance with a combination of both. Notably, these within-person dynamics are not captured by predefined network-traffic features, demonstrating the value of learned representations for longitudinal behavioral sensing. These results establish encrypted network traffic as a viable passive sensing modality, revealing interpretable behavioral dynamics---particularly deviations from an individual's baseline---that are not visible in raw traffic features.
| Comments: | 38 pages, 8 figures. Accepted to Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Vol. 10, No. 4 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Networking and Internet Architecture (cs.NI) |
| ACM classes: | C.2.3; I.2.6; J.3 |
| Cite as: | arXiv:2605.01616 [cs.LG] |
| (or arXiv:2605.01616v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.01616 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3857944
DOI(s) linking to related resources |
Submission history
From: Rameen Mahmood [view email]
[v1]
Sat, 2 May 2026 21:40:07 UTC (355 KB)
[v2]
Fri, 5 Jun 2026 22:55:35 UTC (355 KB)
[v3]
Tue, 6 Oct 2026 21:21:39 UTC (436 KB)
来源：arXiv cs.CY · arxiv.org