Bogdan Carbunar

Users encountering misinformation on social media must decide what to believe and also whether and how to manage an ongoing boundary with the source that shared it. We report a qualitative study with 29 participants from a university community, using an instrumented timeline environment to examine how they interpreted misinformation cues and source-level controls during feed browsing. The sources could retain value after sharing misinformation, and the content was not designed around ideological or identity conflict. Thus, acting on a source required a judgment of its own. We conceptualize deciding whether and how to alter that boundary as accountable boundary work . The framework distinguishes warrant assessment and proportional evaluation as two linked dimensions of judgment, with enactment concerning whether a contemplated boundary move can be carried through. Participants could recognize content as misinformation while preserving the existing source boundary. They also differentiated moves such as filtering and reporting according to whose exposure or relationship would change and whether platform authority could be invoked. Platform design shaped the grounds available for judgment, the interpretation of available controls, and whether contemplated moves were actionable in the flow of the feed. We contribute an interaction-grounded framework for source-level misinformation response, and design and governance implications for legible, socially defensible, and lower-burden boundary management.

Censorship and the distribution of false information, tools used to manipulate what users see and believe, are seemingly at opposite ends of the information access spectrum. Most previous work has examined them in isolation and within individual countries, leaving gaps in our understanding of how these information manipulation tools interact and reinforce each other across diverse societies. In this paper, we study perceptions about the interplay between censorship, false information, and influence operations, gathered through a mixed-methods study consisting of a survey (n = 384) and semi-structured interviews (n = 30) with participants who have experienced these phenomena across diverse countries in both the Global South and Global North, including Bangladesh, China, Cuba, Iran, Venezuela, and the United States. Our findings reveal perceptions of cooperation across various platforms between distinct entities working together to create information cocoons, within which censorship and false information become imperceptible to those affected. Building on study insights, we propose novel platform-level interventions to enhance transparency and help users navigate information manipulation. In addition, we introduce the concept of plausibly deniable social platforms, enabling censored users to provide credible, benign explanations for their activities, protecting them from surveillance and coercion.

Search rank fraud, the fraudulent promotion of products hosted on peer-review sites, is driven by expert workers recruited online, often from crowdsourcing sites. In this paper we introduce the fraud de-anonymization problem, that goes beyond fraud detection, to unmask the human masterminds responsible for posting search rank fraud in peer-review sites. We collect and study data from crowdsourced search rank fraud jobs, and survey the capabilities and behaviors of 58 search rank fraud workers recruited from 6 crowdsourcing sites. We collect a gold standard dataset of Google Play user accounts attributed to 23 crowdsourced workers and analyze their fraudulent behaviors in the wild. We propose Dolos , a fraud de-anonymization system that leverages traits and behaviors we extract from our studies, to attribute detected fraud to crowdsourcing site workers, thus to real identities and bank accounts. We introduce MCDense, a min-cut dense component detection algorithm to uncover groups of user accounts controlled by different workers, and use stylometry and supervised learning to attribute them to crowdsourcing site profiles. Dolos correctly identified the owners of 95 percent of fraud worker-controlled communities, and uncovered fraud workers who promoted as many as 97.5 percent of fraud apps we collected from Google Play. When evaluated on 13,087 apps (820,760 reviews), which we monitored over more than 6 months, Dolos identified 1,056 apps with suspicious reviewer groups. We report orthogonal evidence of their fraud, including fraud duplicates and fraud re-posts. Dolos significantly outperformed adapted dense subgraph detection and loopy belief propagation competitors, on two new coverage scores that measure the quality of detected community partitions.

The difficulty of large-scale monitoring of app markets affects our understanding of their dynamics. This is particularly true for dimensions such as app update frequency, control and pricing, the impact of developer actions on app popularity, as well as coveted membership in top app lists. In this paper, we perform a detailed temporal analysis on two datasets we have collected from the Google Play Store, one consisting of 160000 apps and the other of 87223 newly released apps. We have monitored and collected data about these apps over more than six months. Our results show that a high number of these apps have not been updated over the monitoring interval. Moreover, these apps are controlled by a few developers that dominate the total number of app downloads. We observe that infrequently updated apps significantly impact the median app price. However, a changing app price does not correlate with the download count. Furthermore, we show that apps that attain higher ranks have better stability in top app lists. We show that app market analytics can help detect emerging threat vectors, and identify search rank fraud and even malware. Further, we discuss the research implications of app market analytics on improving developer and user experiences.

Fraudulent behaviors in Google's Android app market fuel search rank abuse and malware proliferation. We present FairPlay, a novel system that uncovers both malware and search rank fraud apps, by picking out trails that fraudsters leave behind. To identify suspicious apps, FairPlay's PCF algorithm correlates review activities and uniquely combines detected review relations with linguistic and behavioral signals gleaned from longitudinal Google Play app data. We contribute a new longitudinal app dataset to the community, which consists of over 87K apps, 2.9M reviews, and 2.4M reviewers, collected over half a year. FairPlay achieves over 95% accuracy in classifying gold standard datasets of malware, fraudulent and legitimate apps. We show that 75% of the identified malware apps engage in search rank fraud. FairPlay discovers hundreds of fraudulent apps that currently evade Google Bouncer's detection technology, and reveals a new type of attack campaign, where users are harassed into writing positive reviews, and install and review other apps.

The popularity and influence of reviews, make sites like Yelp ideal targets for malicious behaviors. We present Marco, a novel system that exploits the unique combination of social, spatial and temporal signals gleaned from Yelp, to detect venues whose ratings are impacted by fraudulent reviews. Marco increases the cost and complexity of attacks, by imposing a tradeoff on fraudsters, between their ability to impact venue ratings and their ability to remain undetected. We contribute a new dataset to the community, which consists of both ground truth and gold standard data. We show that Marco significantly outperforms state‐of‐the‐art approaches, by achieving 94% accuracy in classifying reviews as fraudulent or genuine, and 95.8% accuracy in classifying venues as deceptive or legitimate. Marco successfully flagged 244 deceptive venues from our large dataset with 7,435 venues, 270,121 reviews and 195,417 users. Furthermore, we use Marco to evaluate the impact of Yelp events, organized for elite reviewers, on the hosting venues. We collect data from 149 Yelp elite events throughout the US. We show that two weeks after an event, twice as many hosting venues experience a significant rating boost rather than a negative impact.