# From Packets to Patterns: Interpreting Encrypted Network Traffic as Longitudinal Behavioral Signals

arXiv: https://arxiv.org/abs/2605.01616 · HTML: https://mlsanity.com/paper/2605.01616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 89 references that are in the map.
- First posted on arXiv 2 May 2026.

## Builds on (most cited first, 11 of 11)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [IoT Sentinel: Automated Device-Type Identification for Security Enforcement in IoT](https://mlsanity.com/paper/1611.04880/) (2016)
- [Aper: Evolution-Aware Runtime Permission Misuse Detection for Android Apps](https://mlsanity.com/paper/2201.12542/) (2022)
- [Using mobile phone sensor technology for mental health research: Integrated analysis to identify hidden challenges and potential solutions](https://mlsanity.com/paper/1805.09158/) (2018)
- [Keeping the Smart Home Private with Smart(er) IoT Traffic Shaping](https://mlsanity.com/paper/1812.00955/) (2018)
- [A Systematic Survey on Android API Usage for Data-Driven Analytics with Smartphones](https://mlsanity.com/paper/2104.11271/) (2021)
- [What's on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scale](https://mlsanity.com/paper/2510.13817/) (2025)
- [CareNet: Linking Home-router Network Traffic to DSM-5 Depressive Behavior Indicators](https://mlsanity.com/paper/2511.12772/) (2025)

## Abstract (arXiv)

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.