# Behavioral Fingerprinting and Navigation Prediction in Web Browsing

arXiv: https://arxiv.org/abs/2609.18273 · HTML: https://mlsanity.com/paper/2609.18273/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [A Survey on Session-based Recommender Systems](https://mlsanity.com/paper/1902.04864/) (2019)
- [Session-aware Recommendation: A Surprising Quest for the State-of-the-art](https://mlsanity.com/paper/2011.03424/) (2020)
- [TRACE: Transformer-based user Representations from Attributed Clickstream Event sequences](https://mlsanity.com/paper/2409.12972/) (2024)
- [Browsing behavior exposes identities on the Web](https://mlsanity.com/paper/2312.15489/) (2023)
- [A Public and Reproducible Assessment of the Topics API on Real Data](https://mlsanity.com/paper/2403.19577/) (2024)
- [Web Routineness and Limits of Predictability: Investigating Demographic and Behavioral Differences Using Web Tracking Data](https://mlsanity.com/paper/2012.15112/) (2020)
- [Redefining Website Fingerprinting Attacks With Multiagent LLMs](https://mlsanity.com/paper/2509.12462/) (2025)

## Abstract (arXiv)

Web browsing often appears ephemeral: users visit a few websites, complete a task, and move on. However, even short fragments of browsing activity can contain rich and structured behavioral signals. In this work, we conduct a comparative empirical study of two complementary behavioral inference tasks: session-level user identification and next-domain prediction. Both tasks are derived from the same cleaned event stream and evaluated on large-scale anonymous browsing traces, with sessionization and splitting adapted to the temporal requirements of each task. For user identification, we evaluate classical and neural models operating on session-level behavioral and domain features. For next-domain prediction, we combine graph-based modeling with Large Language Models (LLMs). Experimental results show that short browsing sessions are highly identifiable, while future navigation actions are highly predictable from long-term interaction structure combined with recent behavioral context. Furthermore, LLM-derived semantic features yield only marginal gains over purely structural and sequential models, indicating that repeated interaction patterns remain the dominant predictive signal in the evaluated web-browsing setup. These findings highlight the extent to which interaction history substantially contributes to both user identifiability and navigation predictability in browsing traces.