02 Research

4 items

Publications

01

preprint
arXiv

SST-Guard: Detecting and Characterizing Server-Side Google Analytics in the Wild

Muhammad Jazlan, Alexander Gamero-Garrido, Zubair Shafiq, and Yash Vekaria. 2026. arXiv preprint 2604.27497, April 2026.

As web browsers increasingly restrict client-side tracking, the web tracking ecosystem is shifting from client-side to server-side tracking (SST). In SST, the browser sends tracking requests to an intermediate endpoint, which then forwards them to the tracker's endpoint, eliminating direct client-to-tracker requests. As a result, existing tracking protections that block requests to known tracker endpoints are rendered ineffective. In this paper, we investigate server-side implementation of Google Analytics, the most widely deployed third-party tracking service on the web today. We also present SST-Guard, a multi-modal, browser-based system for detecting and blocking server-side Google Analytics (sGA). Our key insight is that even when the tracker's endpoints change, sGA must necessarily still collect and share the same semantic information as client-side Google Analytics (e.g., identifiers, event metadata). Therefore, rather than detecting requests to known Google Analytics endpoints, SST-Guard aims to detect underlying artifacts of collection and sharing of these semantic values to any arbitrary endpoint. Operationalizing this insight is challenging because real-world sGA deployments commonly customize endpoints and obfuscate URLs/payloads. SST-Guard addresses this challenge using a value-template approach that employs regular expressions to match semantic value patterns across multiple modalities: network requests, cookies, and the window object. We validate SST-Guard on Tranco top-10k websites, detecting 4.02% (403) sGA domains with over 93% accuracy across three modalities, with network request classifier demonstrating the highest accuracy (99.8%). By deploying SST-Guard in the wild, we find 4.21% (6,314) of Tranco top-150k websites using sGA.

arXiv:2604.27497 · write-up

02

preprint
arXiv

Tracking Conversations: Measuring Content and Identity Exposure on AI Chatbots

Muhammad Jazlan, Ethan Wang, Yash Vekaria, and Zubair Shafiq. 2026. arXiv preprint 2604.27438, April 2026.

AI chatbots are becoming a primary interface for seeking information. As their popularity grows, chatbot providers are starting to deploy advertising and analytics. Despite this, tracking on AI chatbots has not been systematically studied. We present a systematic measurement of web tracking on 20 popular AI chatbots. Under controlled settings using a sensitive prompt, we capture and compare network traffic in normal chats and, where supported, private chats. We search for exposure of two categories of information: content, including prompts, prompt-derived titles, chat URLs, and chat identifiers; and identity, including names, emails, account identifiers, first-party cookies, and explicit IP/User-Agent fields in payloads. We find that 17 of 20 chatbots share information with at least one third party. Three chatbots share plaintext conversation text, including both prompt and response snippets, with Microsoft Clarity through session replay. Fifteen chatbots share conversation URLs or chat identifiers with third-party advertising, analytics, or social endpoints. Several chatbots expose user identity through support widgets, analytics, advertising, and session replay tags; in some cases, hashed emails are shared.

arXiv:2604.27438 · write-up

03

poster
ACM IMC 2026

GTM-Config: Reverse Engineering Google Tag Manager in the Wild

Muhammad Jazlan, Eman Nabeel, and Zubair Shafiq. 2026. In Proceedings of the 2026 ACM Internet Measurement Conference (IMC ’26), 1229–1230.

Google Tag Manager (GTM) is the most widely deployed tag management system, observed on 54% of the top 1M websites. GTM compiles a publisher's entire tracking configuration (the pixels to load, the events each pixel tracks, and the rules that determine when those events fire) into a single JavaScript file, gtm.js, served to every visitor. Prior work on GTM has primarily focused on which tags publishers deploy and what traffic those tags generate, with limited attention to the configuration itself. Dynamic analysis recovers it only partially.

We present GTM-Config, a static analysis framework that decodes a website's complete tracking configuration (pixels, events, triggers, and consent gating) from its gtm.js container. We build GTM-Config by iteratively configuring seven major tracking pixels in our own GTM deployment and diffing the compiled containers. We then crawl 32K general, health, and children's websites; 7,277 (22.7%) of them load GTM, and we decode their configurations, comprising roughly 200K tags. Our preliminary analysis shows that 87.1% of websites fire at least one tracking event by default on page load, that only 6.2% consent-gate any event, and that consent-gating mechanisms appear on only 2.9% of health websites, compared to 30.3% of general websites.

doi:10.1145/3777912.3847601 · write-up

04

poster
PETS 2025

WebLLM: Adapting Large Language Models for Anti Tracking

Muhammad Jazlan, Shaoor Munir, Umar Iqbal, Zubair Shafiq, and Sandra Siby. 2025. Poster at PETS 2025, Washington, D.C.

Online tracking has become almost ubiquitous on the web, with 95% desktop and 94% mobile websites containing at least one tracker. Users rely on anti-tracking tools to protect themselves from trackers; however, trackers come up with new techniques to bypass detection by these tools, resulting in a need to develop new detection tools. Previous attempts to solve this problem rely heavily on ground truth, extensive feature engineering, and require a new pipeline for each form of tracking.

In this poster, we explore the feasibility of creating a classification framework to solve the web tracking problem. We use LLMs as they show great promise to domain-specific adaptation. First, we explore prompting engineering approaches a variety of models and find them to be insufficient to beat state of the art methods. Then, we develop a novel prompt optimization pipeline using LLM-based feedback, improving on prompt engineering. Finally, we fine tune Google’s GEMMA 3 models with LoRA and achieve better accuracy than state of the art models for detecting tracking URLs, cookies, and query parameters. We find that LLMs require very little ground truth and do not require any feature engineering. We test this pipeline for different tracking tasks (URL, query parameter classification and cookie classification) and find it works without modification.

webllm.pdf