arXiv subjects

Yash Vekaria

Publications and source records attributed to Yash Vekaria.

16 recordsLinked to original sources

arXiv2026

FP-Agent: Fingerprinting AI Browsing Agents

AI browsing agents are an emerging class of AI-powered bots capable of autonomously navigating websites. Unlike traditional web bots, AI browsing agents typically operate using real browsers and perform everyday tasks, making them difficult to detect. Yet little is known about whether existing AI browsing agents can be distinguished from humans and one another based on their browser or behavioral fingerprints. In this paper, we present the first controlled measurement study of seven AI browsing agents and human users. Using an instrumented honey website, we collect browser and behavioral fingerprint features while AI browsing agents and humans perform three tasks: flight booking, online shopping, and forum interaction. We then train FP-Agent, a multi-class classifier, to evaluate the discriminative power of these features. We find that browser fingerprints provide limited discriminative power when shared by multiple AI browsing agents. Behavioral fingerprints, however, are distinctive: differences in typing, scrolling, and mouse behavior separate AI browsing agents from humans and one another. In a case study evaluating Cloudflare's bot detection, FP-Agent detects all seven AI browsing agents, whereas Cloudflare detects only one. Our findings show that behavioral fingerprints are a critical component to reliably detect and control this emerging form of web traffic.

cs.CR↗

arXiv2026

Tracking Conversations: Measuring Content and Identity Exposure on AI Chatbots

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.

cs.CR↗

arXiv2026

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

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.

cs.CR↗

arXiv2026

Understanding Data Collection, Brokerage, and Spam in the Lead Marketing Ecosystem

The lead marketing ecosystem enables collection, sale, and use of personal data submitted via web forms to deliver personalized quotes in high-value verticals such as insurance. Despite its scale and sensitivity of the collected data, this ecosystem remains largely unexplored by the research community. We present the first empirical study of privacy and spam risks in lead marketing, developing an end-to-end measurement framework to trace data flows from data collection to consumer contact. Our setup instruments over 100 health-related lead-generation websites and monitors 200 controlled phone numbers and email addresses to understand downstream marketing practices. We observe sharing of highly personal and sensitive health information to more than 70 distinct third parties on these lead generation websites. By purchasing our own and other organic leads from three major lead platforms, we uncover deceptive brokerage practices, where consumer data is sold to unvetted buyers and often augmented or fabricated with attributes such as health status and weight. We received a total of over 8,000 telemarketing phone calls, 600 text messages, and 200 emails, where calls often began within seconds of form submission. Many campaigns relied on VoIP-based neighbor spoofing and high-frequency dialing, at times rendering phones unusable. Our experiments with phone and email opt-outs suggest phone-based opt-outs to help the most, although all were ineffective at completely stopping marketing communications. Analysis of 7,432 Better Business Bureau (BBB) complaints and reviews corroborates these findings from the consumer perspective. Overall, our results reveal a highly interconnected and non-compliant lead marketing ecosystem that aggressively monetizes sensitive consumer data.

cs.CR↗

arXiv2026

Keys on Doormats: Exposed API Credentials on the Web

Application programming interfaces (APIs) have become a central part of the modern IT environment, allowing developers to enrich the functionality of applications and interact with third parties such as cloud and payment providers. This interaction often occurs through authentication mechanisms that rely on sensitive credentials such as API keys and tokens that require secure handling. Exposure of these credentials can pose significant consequences to organizations, as malicious attackers can gain access to related services. Previous studies have shown exposure of these sensitive credentials in different environments such as cloud platforms and GitHub. However, the web remains unexplored. In this paper, we study exposure of credentials on the web by analyzing 10M webpages. Our findings reveal that API credentials are widely and publicly exposed on the web, including highly popular and critical webpages such as those of global banks and firmware developers. We identify 1,748 distinct credentials from 14 service providers (e.g., cloud and payment providers) across nearly 10,000 webpages. Moreover, our analysis of archived data suggest credentials to remain exposed for periods ranging from a month to several years. We characterize web-specific exposure vectors and root causes, finding that most originate from JavaScript environments. We also discuss the outcomes of our responsible disclosure efforts that demonstrated a substantial reduction in credential exposure on the web.

cs.CR↗

arXiv2026

PixelConfig: Longitudinal Measurement and Reverse-Engineering of Meta Pixel Configurations

Tracking pixels are used to optimize online ad campaigns through personalization, re-targeting, and conversion tracking. Past research has primarily focused on detecting the prevalence of tracking pixels on the web, with limited attention to how they are configured across websites. A tracking pixel may be configured differently on different websites. In this paper, we present a differential analysis framework: PixelConfig, to reverse-engineer the configurations of Meta Pixel deployments across the web. Using this framework, we investigate three types of Meta Pixel configurations: activity tracking (i.e., what a user is doing on a website), identity tracking (i.e., who a user is or who the device is associated with), and tracking restrictions (i.e., mechanisms to limit the sharing of potentially sensitive information). Using data from the Internet Archive's Wayback Machine, we analyze and compare Meta Pixel configurations on 18K health-related websites with a control group of the top 10K websites from 2017 to 2024. We find that activity tracking features, such as automatic events that collect button clicks and page metadata, and identity tracking features, such as first-party cookies that are unaffected by third-party cookie blocking, reached adoption rates of up to 98.4%, largely driven by the Pixel's default settings. We also find that the Pixel is being used to track potentially sensitive information, such as user interactions related to booking medical appointments and button clicks associated with specific medical conditions (e.g., erectile dysfunction) on health-related websites. Tracking restriction features, such as Core Setup, are configured on up to 34.3% of health websites and 8.7% of control websites. However, even when enabled, these tracking restriction features provide limited protection and can be circumvented in practice.

cs.CR↗

arXiv2026

On the Suitability of LLM-Driven Agents for Dark Pattern Audits

As LLM-driven agents begin to autonomously navigate the web, their ability to interpret and respond to manipulative interface design becomes critical. A fundamental question that emerges is: can such agents reliably recognize patterns of friction, misdirection, and coercion in interface design (i.e., dark patterns)? We study this question in a setting where the workflows are consequential: website portals associated with the submission of CCPA-related data rights requests. These portals operationalize statutory rights, but they are implemented as interactive interfaces whose design can be structured to facilitate, burden, or subtly discourage the exercise of those rights. We design and deploy an LLM-driven auditing agent capable of end-to-end traversal of rights-request workflows, structured evidence gathering, and classification of potential dark patterns. Across a set of 456 data broker websites, we evaluate: (1) the ability of the agent to consistently locate and complete request flows, (2) the reliability and reproducibility of its dark pattern classifications, and (3) the conditions under which it fails or produces poor judgments. Our findings characterize both the feasibility and the limitations of using LLM-driven agents for scalable dark pattern auditing.

cs.CR↗

arXiv2026

Turning Trust to Transactions: Tracking Affiliate Marketing and FTC Compliance in YouTube's Influencer Economy

YouTube has evolved into a powerful platform where creators monetize their influence through affiliate marketing, raising concerns about transparency and ethics, especially when creators fail to disclose their affiliate relationships. Although regulatory agencies like the US Federal Trade Commission (FTC) have issued guidelines to address these issues, non-compliance and consumer harm persist, and the extent of these problems remains unclear. In this paper, we introduce tools, developed with insights from recent advances in Web measurement and NLP research, to examine the state of the affiliate marketing ecosystem on YouTube. We apply these tools to a 10-year dataset of 2 million videos from nearly 540,000 creators, analyzing the prevalence of affiliate marketing on YouTube and the rates of non-compliant behavior. Our findings reveal that affiliate links are widespread, yet disclosure compliance remains low, with most videos failing to meet FTC standards. Furthermore, we analyze the effects of different stakeholders in improving disclosure behavior. Our study suggests that the platform is highly associated with improved compliance through standardized disclosure features. We recommend that regulators and affiliate partners collaborate with platforms to enhance transparency, accountability, and trust in the influencer economy.

cs.CY↗

arXiv2025

SoK: Advances and Open Problems in Web Tracking

Web tracking is a pervasive and opaque practice that enables personalized advertising, retargeting, and conversion tracking. Over time, it has evolved into a sophisticated and invasive ecosystem, employing increasingly complex techniques to monitor and profile users across the web. The research community has a long track record of analyzing new web tracking techniques, designing and evaluating the effectiveness of countermeasures, and assessing compliance with privacy regulations. Despite a substantial body of work on web tracking, the literature remains fragmented across distinctly scoped studies, making it difficult to identify overarching trends, connect new but related techniques, and identify research gaps in the field. Today, web tracking is undergoing a once-in-a-generation transformation, driven by fundamental shifts in the advertising industry, the adoption of anti-tracking countermeasures by browsers, and the growing enforcement of emerging privacy regulations. This Systematization of Knowledge (SoK) aims to consolidate and synthesize this wide-ranging research, offering a comprehensive overview of the technical mechanisms, countermeasures, and regulations that shape the modern and rapidly evolving web tracking landscape. This SoK also highlights open challenges and outlines directions for future research, aiming to serve as a unified reference and introductory material for researchers, practitioners, and policymakers alike.

cs.CR↗

arXiv2025

Big Help or Big Brother? Auditing Tracking, Profiling, and Personalization in Generative AI Assistants

Generative AI (GenAI) browser assistants integrate powerful capabilities of GenAI in web browsers to provide rich experiences such as question answering, content summarization, and agentic navigation. These assistants, available today as browser extensions, can not only track detailed browsing activity such as search and click data, but can also autonomously perform tasks such as filling forms, raising significant privacy concerns. It is crucial to understand the design and operation of GenAI browser extensions, including how they collect, store, process, and share user data. To this end, we study their ability to profile users and personalize their responses based on explicit or inferred demographic attributes and interests of users. We perform network traffic analysis and use a novel prompting framework to audit tracking, profiling, and personalization by the ten most popular GenAI browser assistant extensions. We find that instead of relying on local in-browser models, these assistants largely depend on server-side APIs, which can be auto-invoked without explicit user interaction. When invoked, they collect and share webpage content, often the full HTML DOM and sometimes even the user's form inputs, with their first-party servers. Some assistants also share identifiers and user prompts with third-party trackers such as Google Analytics. The collection and sharing continues even if a webpage contains sensitive information such as health or personal information such as name or SSN entered in a web form. We find that several GenAI browser assistants infer demographic attributes such as age, gender, income, and interests and use this profile--which carries across browsing contexts--to personalize responses. In summary, our work shows that GenAI browser assistants can and do collect personal and sensitive information for profiling and personalization with little to no safeguards.

cs.HC↗

arXiv2025

Auditing the Compliance and Enforcement of Twitter's Advertising Policy

Online platforms have enacted various policies to maintain a safe and trustworthy advertising environment. However, the extent to which these policies are adhered to and enforced remains a subject of interest and concern. In this work, we present a large-scale audit of adult advertising on Twitter (now X), specifically focusing on compliance with its adult (sexual) content advertising policy. Twitter is an interesting case study in that it -- uniquely from other social media platforms -- allows posting of adult content but prohibits adult content in advertising. We analyze approximately 35 thousand ads on Twitter with respect to their compliance to the adult content ad policy through Perspective API and manual annotations. Among other things, we find that nearly 38% of ads violate Twitter's adult content advertising policy, although the platform eventually removed only about 63% of these non-compliant adult ads. We also find inconsistencies in the moderation of such ads across languages, highlighting the need for more reliable and consistent moderation practices across various languages. Overall, our findings highlight blind spots in Twitter's adult ad policy enforcement for certain languages and countries. Our work underscores the importance of external audits to monitor compliance and improve transparency in online advertising.

cs.CY↗

arXiv2024

Watching TV with the Second-Party: A First Look at Automatic Content Recognition Tracking in Smart TVs

Smart TVs implement a unique tracking approach called Automatic Content Recognition (ACR) to profile viewing activity of their users. ACR is a Shazam-like technology that works by periodically capturing the content displayed on a TV's screen and matching it against a content library to detect what content is being displayed at any given point in time. While prior research has investigated third-party tracking in the smart TV ecosystem, it has not looked into second-party ACR tracking that is directly conducted by the smart TV platform. In this work, we conduct a black-box audit of ACR network traffic between ACR clients on the smart TV and ACR servers. We use our auditing approach to systematically investigate whether (1) ACR tracking is agnostic to how a user watches TV (e.g., linear vs. streaming vs. HDMI), (2) privacy controls offered by smart TVs have an impact on ACR tracking, and (3) there are any differences in ACR tracking between the UK and the US. We perform a series of experiments on two major smart TV platforms: Samsung and LG. Our results show that ACR works even when the smart TV is used as a "dumb" external display, opting-out stops network traffic to ACR servers, and there are differences in how ACR works across the UK and the US.

cs.CR↗

arXiv2024

Towards Multi-Stakeholder Vulnerability Notifications in the Ad-Tech Supply Chain

Online advertising relies on a complex and opaque supply chain that involves multiple stakeholders, including advertisers, publishers, and ad-networks, each with distinct and sometimes conflicting incentives. Recent research has demonstrated the existence of ad-tech supply chain vulnerabilities such as dark pooling, where low-quality publishers bundle their ad inventory with higher-quality ones to mislead advertisers. We investigate the effectiveness of vulnerability notification campaigns aimed at mitigating dark pooling. Prior research on vulnerability notifications have primarily explored single-stakeholder contexts, leaving multi-stakeholder scenarios understudied. There is limited attention to complex multi-stakeholder supply chain ecosystems such as ad-tech supply chain, where resolving vulnerabilities often requires coordinated action across entities with misaligned incentives and interdependent roles. We address this gap by implementing the first online advertising supply chain vulnerability notification pipeline to systematically evaluate the responsiveness of various stakeholders in ad-tech supply chain, including publishers, ad-networks, and advertisers to vulnerability notifications by academics and activists. Our nine-month long automated multi-stakeholder notification study shows that notifications are an effective method for reducing dark pooling vulnerabilities in the online advertising ecosystem, especially when targeted towards ad-networks. Further, the sender reputation does not impact responses to notifications from activists and academics in a statistically different way. Overall, our research fosters industry-scale solution to combat ad inventory fraud and fosters future research on feasibility of multi-stakeholder vulnerability notifications in other supply chain ecosystems.

cs.CR↗

arXiv2023

The Inventory is Dark and Full of Misinformation: Understanding the Abuse of Ad Inventory Pooling in the Ad-Tech Supply Chain

Ad-tech enables publishers to programmatically sell their ad inventory to millions of demand partners through a complex supply chain. Bogus or low quality publishers can exploit the opaque nature of the ad-tech to deceptively monetize their ad inventory. In this paper, we investigate for the first time how misinformation sites subvert the ad-tech transparency standards and pool their ad inventory with unrelated sites to circumvent brand safety protections. We find that a few major ad exchanges are disproportionately responsible for the dark pools that are exploited by misinformation websites. We further find evidence that dark pooling allows misinformation sites to deceptively sell their ad inventory to reputable brands. We conclude with a discussion of potential countermeasures such as better vetting of ad exchange partners, adoption of new ad-tech transparency standards that enable end-to-end validation of the ad-tech supply chain, as well as widespread deployment of independent audits like ours.

cs.CR↗

arXiv2021

Under the Spotlight: Web Tracking in Indian Partisan News Websites

India is experiencing intense political partisanship and sectarian divisions. The paper performs, to the best of our knowledge, the first comprehensive analysis on the Indian online news media with respect to tracking and partisanship. We build a dataset of 103 online, mostly mainstream news websites. With the help of two experts, alongside data from the Media Ownership Monitor of the Reporters without Borders, we label these websites according to their partisanship (Left, Right, or Centre). We study and compare user tracking on these sites with different metrics: numbers of cookies, cookie synchronizations, device fingerprinting, and invisible pixel-based tracking. We find that Left and Centre websites serve more cookies than Right-leaning websites. However, through cookie synchronization, more user IDs are synchronized in Left websites than Right or Centre. Canvas fingerprinting is used similarly by Left and Right, and less by Centre. Invisible pixel-based tracking is 50% more intense in Centre-leaning websites than Right, and 25% more than Left. Desktop versions of news websites deliver more cookies than their mobile counterparts. A handful of third-parties are tracking users in most websites in this study. This paper, by demonstrating intense web tracking, has implications for research on overall privacy of users visiting partisan news websites in India.

cs.CY↗

arXiv2021

Differential Tracking Across Topical Webpages of Indian News Media

Online user privacy and tracking have been extensively studied in recent years, especially due to privacy and personal data-related legislations in the EU and the USA, such as the General Data Protection Regulation, ePrivacy Regulation, and California Consumer Privacy Act. Research has revealed novel tracking and personal identifiable information leakage methods that first- and third-parties employ on websites around the world, as well as the intensity of tracking performed on such websites. However, for the sake of scaling to cover a large portion of the Web, most past studies focused on homepages of websites, and did not look deeper into the tracking practices on their topical subpages. The majority of studies focused on the Global North markets such as the EU and the USA. Large markets such as India, which covers 20% of the world population and has no explicit privacy laws, have not been studied in this regard. We aim to address these gaps and focus on the following research questions: Is tracking on topical subpages of Indian news websites different from their homepage? Do third-party trackers prefer to track specific topics? How does this preference compare to the similarity of content shown on these topical subpages? To answer these questions, we propose a novel method for automatic extraction and categorization of Indian news topical subpages based on the details in their URLs. We study the identified topical subpages and compare them with their homepages with respect to the intensity of cookie injection and third-party embeddedness and type. We find differential user tracking among subpages, and between subpages and homepages. We also find a preferential attachment of third-party trackers to specific topics. Also, embedded third-parties tend to track specific subpages simultaneously, revealing possible user profiling in action.

cs.CY↗