analiza aiqbench
This research demonstrates that transformer-based models can extract interpretable behavioral signals—such as stress and loneliness—from encrypted network traffic by learning deviations from individual baselines. The study validates passive sensing as a viable modality for longitudinal health monitoring, leveraging learned representations where traditional traffic features fail to capture within-person dynamics.
From Packets to Patterns: Interpreting Encrypted Network Traffic as Longitudinal Behavioral Signals
arXiv:2605.01616v3 Announce Type: replace 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.
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.
38 pages, 8 figures. Accepted to Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Vol. 10, No. 4
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Networking and Internet Architecture (cs.NI)
C.2.3; I.2.6; J.3
arXiv:2605.01616 [cs.LG]
(or arXiv:2605.01616v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.01616 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1145/3857944 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 328 cuvinte
Subiecte conexe
Learning Behavioral Signals from Encrypted Smartphone Network Traffic
arXiv · 9 iun. 2026
New Windows Backdoor Hides Inside ESET Agent and Wakes Up With a Secret Network Packet
Cybersecurity News · 27 aug. 2026
Lattice-Based Cryptography Explained
Quantum Zeitgeist · 15 aug. 2026
Article: Governing AI in the Cloud: A Practical Guide for Architects
InfoQ · 15 iun. 2026