Actions speak louder than words: Semi-supervised learning for browser fingerprinting detection

TL;DR

This paper introduces a semi-supervised machine learning method for detecting browser fingerprinting scripts, effectively identifying known and new scripts, including previously undetected device-class fingerprinting in the wild.

Contribution

It presents a novel semi-supervised approach that groups scripts by API access patterns, expanding detection beyond heuristics and uncovering new fingerprinting scripts.

Findings

Detected over 94.9% of scripts identified by heuristics

Uncovered fingerprinting scripts missed by heuristics

Identified over 100 device-class fingerprinting scripts in the wild

Abstract

As online tracking continues to grow, existing anti-tracking and fingerprinting detection techniques that require significant manual input must be augmented. Heuristic approaches to fingerprinting detection are precise but must be carefully curated. Supervised machine learning techniques proposed for detecting tracking require manually generated label-sets. Seeking to overcome these challenges, we present a semi-supervised machine learning approach for detecting fingerprinting scripts. Our approach is based on the core insight that fingerprinting scripts have similar patterns of API access when generating their fingerprints, even though their access patterns may not match exactly. Using this insight, we group scripts by their JavaScript (JS) execution traces and apply a semi-supervised approach to detect new fingerprinting scripts. We detail our methodology and demonstrate its ability to identify the majority of scripts ($\geqslant$94.9%) identified by existing heuristic techniques. We also show that the approach expands beyond detecting known scripts by surfacing candidate scripts that are likely to include fingerprinting. Through an analysis of these candidate scripts we discovered fingerprinting scripts that were missed by heuristics and for which there are no heuristics. In particular, we identified over one hundred device-class fingerprinting scripts present on hundreds of domains. To the best of our knowledge, this is the first time device-class fingerprinting has been measured in the wild. These successes illustrate the power of a sparse vector representation and semi-supervised learning to complement and extend existing tracking detection techniques.