1,721,000 research outputs found
Measurement and control of geo-location privacy on Twitter
No full textThe widespread diffusion of Online Social Networks and Media (OSNEM) has generated a huge amount of users’ personal data. As this data is often publicly available, users’ privacy is at risk. To address this issue, users may control the release of their sensitive data on OSNEM. An example of data that users rarely publish is their location. Besides being a privacy-sensitive information, location is a business-relevant data that third parties, e.g., Location-Based Service (LBS) providers, may be interested to obtain. It is, therefore, of paramount importance to understand to what extent the secrecy of location information can be violated. In this work, we investigate how users can measure the privacy of their geo-location on OSNEM and to control the factors affecting it. We define the privacy of a target user as the geographical distance between her actual unexposed location and the location estimated by an attacker. To measure privacy, we propose a novel deep learning architecture that uncovers a target user’s position based only on the publicly-available locations shared by users on Twitter. Results show that locations can be accurately unveiled for the majority of the users, thus suggesting the need for countermeasures to improve their privacy. To control privacy, we propose data perturbation techniques that users can apply to tune the public exposure of their location, and we show the resulting privacy improvements. To shed light on the factors influencing privacy, we then propose a machine learning model that measures privacy based on several users’ features (e.g., social and behavioral characteristics). Unlike the aforementioned deep learning approach, this model also allows to quantify the impact that each feature has on privacy. We observe that features related to the history of users’ visited locations proved to be the most relevant factors affecting privacy. Finally, we explore potential side effects resulting from the application of data perturbation strategies. In particular, we examine, as a study case, the trade-off between users’ privacy and the effectiveness of a proximity marketing LBS. Results suggest that privacy can be guaranteed while not significantly lowering the effectiveness of the LBS
Privacy Leakage and the Manipulation of Public Opinion in Online Social Networks
Full text linkOnline Social Networks (OSNs) are computer-based technologies that enable users to create content, share information, and establish social relationships in online platforms. The advent of OSNs has dramatically revolutionized the way we access the news, share opinion, make business and politics. Although the wide adoption of OSNs brought several positive effects, the combination of its technological and social aspects hides harmful effects for both the individual users and the entire society. Among the potential risks analyzed in the literature (e.g., security, health, etc.), in this thesis, we analyze the perils related to the privacy leakage and the manipulation of opinions in OSNs. In particular, we investigate the factors driving these perils, with the final objective of raising users’ awareness of the risks behind their online activities. We show how, for both the privacy and manipulation perils, social connections play a central role in fostering and exacerbating such issues. In fact, social connections among OSN users result in a network structure, which enables the spreading of information, behaviours, and opinions across the OSN population through online interactions. Along this research direction, we first explore to what extent an individual’s privacy can be violated by leveraging information provided by other users in the OSN. In particular, we examine the problem of location privacy by developing methods to assess users’ privacy risks and strategies to control the public exposure of their data. Then, we explore the privacy peril by considering the diffusion of behaviours and opinions in OSNs. In fact, social interactions can substantially affect the extent to which a behaviour, an opinion, or a product is adopted by OSN users. This concept is a social phenomenon referred to as social influence. According to this concept, we investigate whether social influence modelling (i.e., learning influence strengths among subjects) can be used to accurately predict users’ future activity and, in turn, violate their privacy. We present different approaches to model social influence and we show how such models can be employed to violate users’ privacy. Online interactions and social influence play also a crucial role in the manipulation of peoples’ belief and opinion. Manipulation campaigns have raised particular concerns in the political context. Bots (i.e., software-controlled accounts) and trolls (i.e., state-sponsored human operators) are the main actors responsible for these campaigns. In this thesis, we analyze the activity of such malicious actors to enhance and enable countermeasures for their detection. More specifically, we first uncover the strategies employed by bots to avoid detection and manipulate human users. Then, we present an approach for detecting trolls’ activity in OSNs that accurately identifies troll accounts and unveils their distinguishing behaviour with respect to regular users. The results presented in this thesis confirm the privacy and manipulation risks in OSNs: On one hand, we prove that users’ privacy is not under individual control as public information can be efficiently used to predict their behaviour, and in turn, violate their privacy. On the other hand, we show that malicious actors have become increasingly sophisticated to escape detection andmanipulate human users. However, the majority of OSN users are not conscious or underestimate the potential risks behind their online activity. Towards raising users’ awareness of such perils and to mitigate this set of open problems, we propose an awareness service, based on a mobile application, to timely communicate users their current risks in OSNs. For this purpose, we deploy a framework to collect users’ data in a privacy-preserving way and provide them with feedback about their privacy and manipulation risks in real-time
Uncovering coordinated cross-platform information operations: Threatening the integrity of the 2024 U.S. presidential election
No full textInformation operations (IOs) pose a significant threat to the integrity of democratic processes, with the potential to influence election-related online discourse. In anticipation of the 2024 U.S. presidential election, we present a study aimed at uncovering the digital tracesof coordinated IOs on X (formerly Twitter). Using our machine learning framework for detecting online coordination, we analyze adataset comprising election-related conversations on X from May to July 2024. This reveals a network of coordinated inauthenticactors, displaying notable similarities in their link-sharing behaviors. Our analysis shows concerted efforts by these accounts todisseminate misleading, redundant, and biased information across the Web through a coordinated cross-platform information operation:The links shared by this network frequently direct users to other social media platforms or mock news sites featuring low-qualitypolitical content and, in turn, promoting the same X and YouTube accounts. Members of this network also shared deceptive imagesgenerated by AI, accompanied by language attacking political figures and symbolic imagery intended to convey power and dominance.While X has suspended or restricted a subset of these accounts, 75 percent of the coordinated network remains active, garneringsubstantial traction over time: The suspicious Web sites promoted by this coordinated network are shared thousands of times per day bythe X user base, further amplifying their reach and potential impact. Our findings underscore the critical role of developingcomputational models to scale up the detection of threats on large social media platforms, and emphasize the broader implications ofthese techniques to detect IOs across the wider Web
Exposing Cross-Platform Coordinated Inauthentic Activity in the Run-Up to the 2024 U.S. Election
No full textPropaganda and Misinformation on Facebook and Twitter during the Russian Invasion of Ukraine
Full text linkIOHunter: Graph Foundation Model to Uncover Online Information Operations
No full textSocial media platforms have become vital spaces for public discourse, serving as modern agorás where a wide range of voices influence societal narratives. However, their open nature also makes them vulnerable to exploitation by malicious actors, including state-sponsored entities, who can conduct information operations (IOs) to manipulate public opinion.
The spread of misinformation, false news, and misleading claims threatens democratic processes and societal cohesion, making it crucial to develop methods for the timely detection of inauthentic activity to protect the integrity of online discourse. In this work, we introduce a methodology designed to identify users orchestrating information operations, a.k.a. IO drivers, across various influence campaigns. Our framework, named IOHunter, leverages the combined strengths of Language Models and Graph Neural Networks to improve generalization in supervised, scarcely-supervised, and cross-IO contexts. Our approach achieves state-of-the-art performance across multiple sets of IOs originating from six countries, significantly surpassing existing approaches. This research marks a step toward developing Graph Foundation Models specifically tailored for the task of IO detection on social media platforms
How does Twitter account moderation work? Dynamics of account creation and suspension on Twitter during major geopolitical events
Full text linkSocial media moderation policies are often at the center of public debate,
and their implementation and enactment are sometimes surrounded by a veil of
mystery. Unsurprisingly, due to limited platform transparency and data access,
relatively little research has been devoted to characterizing moderation
dynamics, especially in the context of controversial events and the platform
activity associated with them. Here, we study the dynamics of account creation
and suspension on Twitter during two global political events: Russia's invasion
of Ukraine and the 2022 French Presidential election. Leveraging a large-scale
dataset of 270M tweets shared by 16M users in multiple languages over several
months, we identify peaks of suspicious account creation and suspension, and we
characterize behaviours that more frequently lead to account suspension. We
show how large numbers of accounts get suspended within days from their
creation. Suspended accounts tend to mostly interact with legitimate users, as
opposed to other suspicious accounts, often making unwarranted and excessive
use of reply and mention features, and predominantly sharing spam and harmful
content. While we are only able to speculate about the specific causes leading
to a given account suspension, our findings shed light on patterns of platform
abuse and subsequent moderation during major events.Comment: See published version at EPJ Data Scienc
Infer mobility patterns and social dynamics for modelling human behaviour
No full textInvestigating human mobility patterns and comprehending the social dynamics that govern people movements is of high interest for multiple aspects and reasons. Location-based services, mobile network management, and urban planning are just few of the several applications that benefit from this kind of assessment. This work focuses on the stochastic analysis of spatiotemporal and social network data in order to build a human behaviour model which aims to predict social dynamics and to infer users’ mobility patterns and interests
Identifying and Characterizing Behavioral Classes of Radicalization within the QAnon Conspiracy on Twitter
Full text linkSocial media provide a fertile ground where conspiracy theories and radical ideas can flourish, reach broad audiences, and sometimes lead to hate or violence beyond the online world itself.
QAnon represents a notable example of a political conspiracy that started out on social media but turned mainstream, in part due to public endorsement by influential political figures. Nowadays, QAnon conspiracies often appear in the news, are part of political rhetoric, and are espoused by significant swaths of people in the United States. It is therefore crucial to understand how such a conspiracy took root online, and what led so many social media users to adopt its ideas. In this work, we propose a framework that exploits both social interaction and content signals to uncover evidence of user radicalization or support for QAnon. Leveraging a large dataset of 240M tweets collected in the run-up to the 2020 US Presidential election, we define and validate a multivariate metric of radicalization. We use that to separate users in distinct, naturally-emerging, classes of behaviors associated with radicalization processes, from self-declared QAnon supporters to hyper-active conspiracy promoters. We also analyze the impact of Twitter's moderation policies on the interactions among different classes: we discover aspects of moderation that succeed, yielding a substantial reduction in the endorsement received by hyperactive QAnon accounts. But we also uncover where moderation fails, showing how QAnon content amplifiers are not deterred or affected by the Twitter intervention. Our findings refine our understanding of online radicalization processes, reveal effective and ineffective aspects of moderation, and call for the need to further investigate the role social media play in the spread of conspiracies
- …
