Bolun Wang

Whispers in the dark: analysis of an anonymous social network

Social interactions and interpersonal communication has undergone significant changes in recent years. Increasing awareness of privacy issues and events such as the Snowden disclosures have led to the rapid growth of a new generation of anonymous social networks and messaging applications. By removing traditional concepts of strong identities and social links, these services encourage communication between strangers, and allow users to express themselves without fear of bullying or retaliation. Despite millions of users and billions of monthly page views, there is little empirical analysis of how services like Whisper have changed the shape and content of social interactions. In this paper, we present results of the first large-scale empirical study of an anonymous social network, using a complete 3-month trace of the Whisper network covering 24 million whispers written by more than 1 million unique users. We seek to understand how anonymity and the lack of social links affect user behavior. We analyze Whisper from a number of perspectives, including the structure of user interactions in the absence of persistent social links, user engagement and network stickiness over time, and content moderation in a network with minimal user accountability. Finally, we identify and test an attack that exposes Whisper users to detailed location tracking. We have notified Whisper and they have taken steps to address the problem.

Value and Misinformation in Collaborative Investing Platforms

It is often difficult to separate the highly capable “experts” from the average worker in crowdsourced systems. This is especially true for challenge application domains that require extensive domain knowledge. The problem of stock analysis is one such domain, where even the highly paid, well-educated domain experts are prone to make mistakes. As an extremely challenging problem space, the “wisdom of the crowds” property that many crowdsourced applications rely on may not hold. In this article, we study the problem of evaluating and identifying experts in the context of SeekingAlpha and StockTwits, two crowdsourced investment services that have recently begun to encroach on a space dominated for decades by large investment banks. We seek to understand the quality and impact of content on collaborative investment platforms, by empirically analyzing complete datasets of SeekingAlpha articles (9 years) and StockTwits messages (4 years). We develop sentiment analysis tools and correlate contributed content to the historical performance of relevant stocks. While SeekingAlpha articles and StockTwits messages provide minimal correlation to stock performance in aggregate, a subset of experts contribute more valuable (predictive) content. We show that these authors can be easily identified by user interactions, and investments based on their analysis significantly outperform broader markets. This effectively shows that even in challenging application domains, there is a secondary or indirect wisdom of the crowds. Finally, we conduct a user survey that sheds light on users’ views of SeekingAlpha content and stock manipulation. We also devote efforts to identify potential manipulation of stocks by detecting authors controlling multiple identities.

The power of comments: fostering social interactions in microblog networks

Today’s ubiquitous online social networks serve multiple purposes, including social communication (Facebook, Renren), and news dissemination (Twitter). But how does a social network’s design define its functionality? Answering this would need social network providers to take a proactive role in defining and guiding user behavior.In this paper, we first take a step to answer this question with a data-driven approach, through measurement and analysis of the Sina Weibo microblogging service. Often compared to Twitter because of its format,Weibo is interesting for our analysis because it serves as a social communication tool and a platform for news dissemination, too. While similar to Twitter in functionality, Weibo provides a distinguishing feature, comments, allowing users to form threaded conversations around a single tweet. Our study focuses on this feature, and how it contributes to interactions and improves social engagement.We use analysis of comment interactions to uncover their role in social interactivity, and use comment graphs to demonstrate the structure of Weibo users interactions. Finally, we present a case study that shows the impact of comments in malicious user detection, a key application on microblogging systems. That is, using properties of comments significantly improves the accuracy in both modeling Received May 20, 2015; accepted October 29, 2015 E-mail: chenyang@fudan.edu.cn and detection of malicious users.

Ghost Riders: Sybil Attacks on Crowdsourced Mobile Mapping Services

Real-time crowdsourced maps, such as Waze provide timely updates on traffic, congestion, accidents, and points of interest. In this paper, we demonstrate how lack of strong location authentication allows creation of software-based Sybil devices that expose crowdsourced map systems to a variety of security and privacy attacks. Our experiments show that a single Sybil device with limited resources can cause havoc on Waze, reporting false congestion and accidents and automatically rerouting user traffic. More importantly, we describe techniques to generate Sybil devices at scale, creating armies of virtual vehicles capable of remotely tracking precise movements for large user populations while avoiding detection. To defend against Sybil devices, we propose a new approach based on co-location edges, authenticated records that attest to the one-time physical co-location of a pair of devices. Over time, co-location edges combine to form large proximity graphs that attest to physical interactions between devices, allowing scalable detection of virtual vehicles. We demonstrate the efficacy of this approach using large-scale simulations, and how they can be used to dramatically reduce the impact of the attacks. We have informed Waze/Google team of our research findings. Currently, we are in active collaboration with Waze team to improve the security and privacy of their system.

Complexity vs. performance: empirical analysis of machine learning as a service

Machine learning classifiers are basic research tools used in numerous types of network analysis and modeling. To reduce the need for domain expertise and costs of running local ML classifiers, network researchers can instead rely on centralized Machine Learning as a Service (MLaaS) platforms. In this paper, we evaluate the effectiveness of MLaaS systems ranging from fully-automated, turnkey systems to fully-customizable systems, and find that with more user control comes greater risk. Good decisions produce even higher performance, and poor decisions result in harsher performance penalties. We also find that server side optimizations help fully-automated systems outperform default settings on competitors, but still lag far behind well-tuned MLaaS systems which compare favorably to standalone ML libraries. Finally, we find classifier choice is the dominating factor in determining model performance, and that users can approximate the performance of an optimal classifier choice by experimenting with a small subset of random classifiers. While network researchers should approach MLaaS systems with caution, they can achieve results comparable to standalone classifiers if they have sufficient insight into key decisions like classifiers and feature selection.