Duumviri: Detecting Trackers and Mixed Trackers with a Breakage Detector
He Shuang
Network and Distributed System Security (NDSS) Symposium 2025 · Day 1 · Web Security
In the realm of digital privacy, the pervasive issue of online tracking continues to challenge users and developers alike. While content blockers have become a staple for many, their reliance on manually curated filter lists presents significant limitations, particularly in scalability and the potential for human error. This talk, presented by He Shuang at the NDSS Symposium, introduces **Duumviri**, a novel approach to automated tracker detection that fundamentally rethinks the problem. Duumviri distinguishes itself by proposing a **two-model system**: a traditional tracker detector paired with an innovative **breakage detector**.
AI review
Duumviri is legitimate academic security research solving a real problem — high breakage rates in automated tracker detection — with a clever two-model architecture and a genuinely novel training data strategy. Solid NDSS-tier systems work, but it's niche enough and incremental enough that it fills a conference slot without threatening to redefine anyone's practice.