arXiv subjects

Zubair Shafiq

Publications and source records attributed to Zubair Shafiq.

51 records · Page 3Linked to original sources

arXiv2021

HARPO: Learning to Subvert Online Behavioral Advertising

Online behavioral advertising, and the associated tracking paraphernalia, poses a real privacy threat. Unfortunately, existing privacy-enhancing tools are not always effective against online advertising and tracking. We propose Harpo, a principled learning-based approach to subvert online behavioral advertising through obfuscation. Harpo uses reinforcement learning to adaptively interleave real page visits with fake pages to distort a tracker's view of a user's browsing profile. We evaluate Harpo against real-world user profiling and ad targeting models used for online behavioral advertising. The results show that Harpo improves privacy by triggering more than 40% incorrect interest segments and 6x higher bid values. Harpo outperforms existing obfuscation tools by as much as 16x for the same overhead. Harpo is also able to achieve better stealthiness to adversarial detection than existing obfuscation tools. Harpo meaningfully advances the state-of-the-art in leveraging obfuscation to subvert online behavioral advertising

cs.LG↗

arXiv2021

Avengers Ensemble! Improving Transferability of Authorship Obfuscation

Stylometric approaches have been shown to be quite effective for real-world authorship attribution. To mitigate the privacy threat posed by authorship attribution, researchers have proposed automated authorship obfuscation approaches that aim to conceal the stylometric artefacts that give away the identity of an anonymous document's author. Recent work has focused on authorship obfuscation approaches that rely on black-box access to an attribution classifier to evade attribution while preserving semantics. However, to be useful under a realistic threat model, it is important that these obfuscation approaches work well even when the adversary's attribution classifier is different from the one used internally by the obfuscator. Unfortunately, existing authorship obfuscation approaches do not transfer well to unseen attribution classifiers. In this paper, we propose an ensemble-based approach for transferable authorship obfuscation. Our experiments show that if an obfuscator can evade an ensemble attribution classifier, which is based on multiple base attribution classifiers, it is more likely to transfer to different attribution classifiers. Our analysis shows that ensemble-based authorship obfuscation achieves better transferability because it combines the knowledge from each of the base attribution classifiers by essentially averaging their decision boundaries.

cs.LG↗

arXiv2021

TrackerSift: Untangling Mixed Tracking and Functional Web Resources

Trackers have recently started to mix tracking and functional resources to circumvent privacy-enhancing content blocking tools. Such mixed web resources put content blockers in a bind: risk breaking legitimate functionality if they act and risk missing privacy-invasive advertising and tracking if they do not. In this paper, we propose TrackerSift to progressively classify and untangle mixed web resources (that combine tracking and legitimate functionality) at multiple granularities of analysis (domain, hostname, script, and method). Using TrackerSift, we conduct a large-scale measurement study of such mixed resources on 100K websites. We find that more than 17% domains, 48% hostnames, 6% scripts, and 9% methods observed in our crawls combine tracking and legitimate functionality. While mixed web resources are prevalent across all granularities, TrackerSift is able to attribute 98% of the script-initiated network requests to either tracking or functional resources at the finest method-level granularity. Our analysis shows that mixed resources at different granularities are typically served from CDNs or as inlined and bundled scripts, and that blocking them indeed results in breakage of legitimate functionality. Our results highlight opportunities for finer-grained content blocking to remove mixed resources without breaking legitimate functionality.

cs.NI↗

arXiv2021

WebGraph: Capturing Advertising and Tracking Information Flows for Robust Blocking

Millions of web users directly depend on ad and tracker blocking tools to protect their privacy. However, existing ad and tracker blockers fall short because of their reliance on trivially susceptible advertising and tracking content. In this paper, we first demonstrate that the state-of-the-art machine learning based ad and tracker blockers, such as AdGraph, are susceptible to adversarial evasions deployed in real-world. Second, we introduce WebGraph, the first graph-based machine learning blocker that detects ads and trackers based on their action rather than their content. By building features around the actions that are fundamental to advertising and tracking - storing an identifier in the browser, or sharing an identifier with another tracker - WebGraph performs nearly as well as prior approaches, but is significantly more robust to adversarial evasions. In particular, we show that WebGraph achieves comparable accuracy to AdGraph, while significantly decreasing the success rate of an adversary from near-perfect under AdGraph to around 8% under WebGraph. Finally, we show that WebGraph remains robust to a more sophisticated adversary that uses evasion techniques beyond those currently deployed on the web.

cs.CR↗

arXiv2021

Fingerprinting Fine-tuned Language Models in the Wild

There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, disinformation, or propaganda. Therefore, the research community is actively working on developing approaches to detect whether a given text is organic or synthetic. While this is a useful first step, it is important to be able to further fingerprint the author LM to attribute its origin. Prior work on fingerprinting LMs is limited to attributing synthetic text generated by a handful (usually < 10) of pre-trained LMs. However, LMs such as GPT2 are commonly fine-tuned in a myriad of ways (e.g., on a domain-specific text corpus) before being used to generate synthetic text. It is challenging to fingerprinting fine-tuned LMs because the universe of fine-tuned LMs is much larger in realistic scenarios. To address this challenge, we study the problem of large-scale fingerprinting of fine-tuned LMs in the wild. Using a real-world dataset of synthetic text generated by 108 different fine-tuned LMs, we conduct comprehensive experiments to demonstrate the limitations of existing fingerprinting approaches. Our results show that fine-tuning itself is the most effective in attributing the synthetic text generated by fine-tuned LMs.

cs.CL↗

arXiv2020

Understanding Incentivized Mobile App Installs on Google Play Store

"Incentivized" advertising platforms allow mobile app developers to acquire new users by directly paying users to install and engage with mobile apps (e.g., create an account, make in-app purchases). Incentivized installs are banned by the Apple App Store and discouraged by the Google Play Store because they can manipulate app store metrics (e.g., install counts, appearance in top charts). Yet, many organizations still offer incentivized install services for Android apps. In this paper, we present the first study to understand the ecosystem of incentivized mobile app install campaigns in Android and its broader ramifications through a series of measurements. We identify incentivized install campaigns that require users to install an app and perform in-app tasks targeting manipulation of a wide variety of user engagement metrics (e.g., daily active users, user session lengths) and revenue. Our results suggest that these artificially inflated metrics can be effective in improving app store metrics as well as helping mobile app developers to attract funding from venture capitalists. Our study also indicates lax enforcement of the Google Play Store's existing policies to prevent these behaviors. It further motivates the need for stricter policing of incentivized install campaigns. Our proposed measurements can also be leveraged by the Google Play Store to identify potential policy violations.

cs.CY↗

arXiv2020

Fingerprinting the Fingerprinters: Learning to Detect Browser Fingerprinting Behaviors

Browser fingerprinting is an invasive and opaque stateless tracking technique. Browser vendors, academics, and standards bodies have long struggled to provide meaningful protections against browser fingerprinting that are both accurate and do not degrade user experience. We propose FP-Inspector, a machine learning based syntactic-semantic approach to accurately detect browser fingerprinting. We show that FP-Inspector performs well, allowing us to detect 26% more fingerprinting scripts than the state-of-the-art. We show that an API-level fingerprinting countermeasure, built upon FP-Inspector, helps reduce website breakage by a factor of 2. We use FP-Inspector to perform a measurement study of browser fingerprinting on top-100K websites. We find that browser fingerprinting is now present on more than 10% of the top-100K websites and over a quarter of the top-10K websites. We also discover previously unreported uses of JavaScript APIs by fingerprinting scripts suggesting that they are looking to exploit APIs in new and unexpected ways.

cs.CR↗

arXiv2020

CanaryTrap: Detecting Data Misuse by Third-Party Apps on Online Social Networks

Online social networks support a vibrant ecosystem of third-party apps that get access to personal information of a large number of users. Despite several recent high-profile incidents, methods to systematically detect data misuse by third-party apps on online social networks are lacking. We propose CanaryTrap to detect misuse of data shared with third-party apps. CanaryTrap associates a honeytoken to a user account and then monitors its unrecognized use via different channels after sharing it with the third-party app. We design and implement CanaryTrap to investigate misuse of data shared with third-party apps on Facebook. Specifically, we share the email address associated with a Facebook account as a honeytoken by installing a third-party app. We then monitor the received emails and use Facebook's ad transparency tool to detect any unrecognized use of the shared honeytoken. Our deployment of CanaryTrap to monitor 1,024 Facebook apps has uncovered multiple cases of misuse of data shared with third-party apps on Facebook including ransomware, spam, and targeted advertising.

cs.CY↗

arXiv2020

A Girl Has A Name: Detecting Authorship Obfuscation

Authorship attribution aims to identify the author of a text based on the stylometric analysis. Authorship obfuscation, on the other hand, aims to protect against authorship attribution by modifying a text's style. In this paper, we evaluate the stealthiness of state-of-the-art authorship obfuscation methods under an adversarial threat model. An obfuscator is stealthy to the extent an adversary finds it challenging to detect whether or not a text modified by the obfuscator is obfuscated - a decision that is key to the adversary interested in authorship attribution. We show that the existing authorship obfuscation methods are not stealthy as their obfuscated texts can be identified with an average F1 score of 0.87. The reason for the lack of stealthiness is that these obfuscators degrade text smoothness, as ascertained by neural language models, in a detectable manner. Our results highlight the need to develop stealthy authorship obfuscation methods that can better protect the identity of an author seeking anonymity.

cs.CL↗

arXiv2020

Characterizing Smart Home IoT Traffic in the Wild

As the smart home IoT ecosystem flourishes, it is imperative to gain a better understanding of the unique challenges it poses in terms of management, security, and privacy. Prior studies are limited because they examine smart home IoT devices in testbed environments or at a small scale. To address this gap, we present a measurement study of smart home IoT devices in the wild by instrumenting home gateways and passively collecting real-world network traffic logs from more than 200 homes across a large metropolitan area in the United States. We characterize smart home IoT traffic in terms of its volume, temporal patterns, and external endpoints along with focusing on certain security and privacy concerns. We first show that traffic characteristics reflect the functionality of smart home IoT devices such as smart TVs generating high volume traffic to content streaming services following diurnal patterns associated with human activity. While the smart home IoT ecosystem seems fragmented, our analysis reveals that it is mostly centralized due to its reliance on a few popular cloud and DNS services. Our findings also highlight several interesting security and privacy concerns in smart home IoT ecosystem such as the need to improve policy-based access control for IoT traffic, lack of use of application layer encryption, and prevalence of third-party advertising and tracking services. Our findings have important implications for future research on improving management, security, and privacy of the smart home IoT ecosystem.

cs.NI↗

arXiv2020

A4 : Evading Learning-based Adblockers

Efforts by online ad publishers to circumvent traditional ad blockers towards regaining fiduciary benefits, have been demonstrably successful. As a result, there have recently emerged a set of adblockers that apply machine learning instead of manually curated rules and have been shown to be more robust in blocking ads on websites including social media sites such as Facebook. Among these, AdGraph is arguably the state-of-the-art learning-based adblocker. In this paper, we develop A4, a tool that intelligently crafts adversarial samples of ads to evade AdGraph. Unlike the popular research on adversarial samples against images or videos that are considered less- to un-restricted, the samples that A4 generates preserve application semantics of the web page, or are actionable. Through several experiments we show that A4 can bypass AdGraph about 60% of the time, which surpasses the state-of-the-art attack by a significant margin of 84.3%; in addition, changes to the visual layout of the web page due to these perturbations are imperceptible. We envision the algorithmic framework proposed in A4 is also promising in improving adversarial attacks against other learning-based web applications with similar requirements.

cs.CR↗

arXiv2019

The TV is Smart and Full of Trackers: Towards Understanding the Smart TV Advertising and Tracking Ecosystem

Motivated by the growing popularity of smart TVs, we present a large-scale measurement study of smart TVs by collecting and analyzing their network traffic from two different vantage points. First, we analyze aggregate network traffic of smart TVs in-the-wild, collected from residential gateways of tens of homes and several different smart TV platforms, including Apple, Samsung, Roku, and Chromecast. In addition to accessing video streaming and cloud services, we find that smart TVs frequently connect to well-known as well as platform-specific advertising and tracking services (ATS). Second, we instrument Roku and Amazon Fire TV, two popular smart TV platforms, by setting up a controlled testbed to systematically exercise the top-1000 apps on each platform, and analyze their network traffic at the granularity of the individual apps. We again find that smart TV apps connect to a wide range of ATS, and that the key players of the ATS ecosystems of the two platforms are different from each other and from that of the mobile platform. Third, we evaluate the (in)effectiveness of state-of-the-art DNS-based blocklists in filtering advertising and tracking traffic for smart TVs. We find that personally identifiable information (PII) is exfiltrated to platform-related Internet endpoints and third parties, and that blocklists are generally better at preventing exposure of PII to third parties than to platform-related endpoints. Our work demonstrates the segmentation of the smart TV ATS ecosystem across platforms and its differences from the mobile ATS ecosystem, thus motivating the need for designing privacy-enhancing tools specifically for each smart TV platform.

cs.NI↗

arXiv2019

Inferring Tracker-Advertiser Relationships in the Online Advertising Ecosystem using Header Bidding

Online advertising relies on trackers and data brokers to show targeted ads to users. To improve targeting, different entities in the intricately interwoven online advertising and tracking ecosystems are incentivized to share information with each other through client-side or server-side mechanisms. Inferring data sharing between entities, especially when it happens at the server-side, is an important and challenging research problem. In this paper, we introduce KASHF: a novel method to infer data sharing relationships between advertisers and trackers by studying how an advertiser's bidding behavior changes as we manipulate the presence of trackers. We operationalize this insight by training an interpretable machine learning model that uses the presence of trackers as features to predict the bidding behavior of an advertiser. By analyzing the machine learning model, we are able to infer relationships between advertisers and trackers irrespective of whether data sharing occurs at the client-side or the server-side. We are also able to identify several server-side data sharing relationships that are validated externally but are not detected by client-side cookie syncing.

cs.CY↗

arXiv2019

AdGraph: A Graph-Based Approach to Ad and Tracker Blocking

User demand for blocking advertising and tracking online is large and growing. Existing tools, both deployed and described in research, have proven useful, but lack either the completeness or robustness needed for a general solution. Existing detection approaches generally focus on only one aspect of advertising or tracking (e.g. URL patterns, code structure), making existing approaches susceptible to evasion. In this work we present AdGraph, a novel graph-based machine learning approach for detecting advertising and tracking resources on the web. AdGraph differs from existing approaches by building a graph representation of the HTML structure, network requests, and JavaScript behavior of a webpage, and using this unique representation to train a classifier for identifying advertising and tracking resources. Because AdGraph considers many aspects of the context a network request takes place in, it is less susceptible to the single-factor evasion techniques that flummox existing approaches. We evaluate AdGraph on the Alexa top-10K websites, and find that it is highly accurate, able to replicate the labels of human-generated filter lists with 95.33% accuracy, and can even identify many mistakes in filter lists. We implement AdGraph as a modification to Chromium. AdGraph adds only minor overhead to page loading and execution, and is actually faster than stock Chromium on 42% of websites and AdBlock Plus on 78% of websites. Overall, we conclude that AdGraph is both accurate enough and performant enough for online use, breaking comparable or fewer websites than popular filter list based approaches.

cs.CY↗

arXiv2016

GraphPrints: Towards a Graph Analytic Method for Network Anomaly Detection

This paper introduces a novel graph-analytic approach for detecting anomalies in network flow data called GraphPrints. Building on foundational network-mining techniques, our method represents time slices of traffic as a graph, then counts graphlets -- small induced subgraphs that describe local topology. By performing outlier detection on the sequence of graphlet counts, anomalous intervals of traffic are identified, and furthermore, individual IPs experiencing abnormal behavior are singled-out. Initial testing of GraphPrints is performed on real network data with an implanted anomaly. Evaluation shows false positive rates bounded by 2.84% at the time-interval level, and 0.05% at the IP-level with 100% true positive rates at both.

cs.CR↗