Motivated by a strongly growing interest in anonymizing social network data, we investigate the NP-hard Degree Anonymization problem: given an undirected graph, the task is to add a minimum number of edges such that the graph becomes k-anonymous. That is, for each vertex there have to be at least k-1 other vertices of exactly the same degree. The model of degree anonymization has been introduced by Liu and Terzi [ACM SIGMOD'08], who also proposed and evaluated a two-phase heuristic. We present an enhancement of this heuristic, including new algorithms for each phase which significantly improve on the previously known theoretical and practical running times. Moreover, our algorithms are optimized for large-scale social networks and provide upper and lower bounds for the optimal solution. Notably, on about 26 % of the real-world data we provide (provably) optimal solutions; whereas in the other cases our upper bounds significantly improve on known heuristic solutions.
It is important to study the risks of publishing privacy-sensitive data. Even if sensitive identities (e.g., name, social security number) were removed and advanced data perturbation techniques were applied, several de-anonymization attacks have been proposed to re-identify individuals. However, existing attacks have some limitations: 1) they are limited in de-anonymization accuracy; 2) they require prior seed knowledge and suffer from the imprecision of such seed information. We propose a novel structure-based de-anonymization attack, which does not require the attacker to have prior informat…
Following the trend of data trading and data publishing, many online social networks have enabled potentially sensitive data to be exchanged or shared on the web. As a result, users' privacy could be exposed to malicious third parties since they are extremely vulnerable to de-anonymization attacks, i.e., the attacker links the anonymous nodes in the social network to their real identities with the help of background knowledge. Previous work in social network de-anonymization mostly focuses on designing accurate and efficient de-anonymization methods. We study this topic from a different perspe…
The risks of publishing privacy-sensitive data have received considerable attention recently. Several de-anonymization attacks have been proposed to re-identify individuals even if data anonymization techniques were applied. However, there is no theoretical quantification for relating the data utility that is preserved by the anonymization techniques and the data vulnerability against de-anonymization attacks. In this paper, we theoretically analyze the de-anonymization attacks and provide conditions on the utility of the anonymized data (denoted by anonymized utility) to achieve successful de…
In this paper, de-anonymizing internet users by actively querying their group memberships in social networks is considered. In this problem, an anonymous victim visits the attacker's website, and the attacker uses the victim's browser history to query her social media activity for the purpose of de-anonymization using the minimum number of queries. A stochastic model of the problem is considered where the attacker has partial prior knowledge of the group membership graph and receives noisy responses to its real-time queries. The victim's identity is assumed to be chosen randomly based on a giv…
We present a generic and automated approach to re-identifying nodes in anonymized social networks which enables novel anonymization techniques to be quickly evaluated. It uses machine learning (decision forests) to matching pairs of nodes in disparate anonymized sub-graphs. The technique uncovers artefacts and invariants of any black-box anonymization scheme from a small set of examples. Despite a high degree of automation, classification succeeds with significant true positive rates even when small false positive rates are sought. Our evaluation uses publicly available real world datasets to …
Releasing connection data from social networking services can pose a significant threat to user privacy. In our work, we consider structural social network de-anonymization attacks, which are used when a malicious party uses connections in a public or other identified network to re-identify users in an anonymized social network release that he obtained previously. In this paper we design and evaluate a novel social de-anonymization attack. In particular, we argue that the similarity function used to re-identify nodes is a key component of such attacks, and we design a novel measure tailored fo…
Graph clustering is widely used in many data analysis applications. In this paper we propose several parallel graph clustering algorithms based on Monte Carlo simulations and expectation maximization in the context of stochastic block models. We apply those algorithms to the specific problems of recommender systems and social network anonymization. We compare the experimental results to previous propositions.
Social graphs derived from online social interactions contain a wealth of information that is nowadays extensively used by both industry and academia. However, as social graphs contain sensitive information, they need to be properly anonymized before release. Most of the existing graph anonymization mechanisms rely on the perturbation of the original graph's edge set. In this paper, we identify a fundamental weakness of these mechanisms: They neglect the strong structural proximity between friends in social graphs, thus add implausible fake edges for anonymization. To exploit this weakness, we…
Anonymized social network graphs published for academic or advertisement purposes are subject to de-anonymization attacks by leveraging side information in the form of a second, public social network graph correlated with the anonymized graph. This is because the two are from the same underlying graph of true social relationships. In this paper, we (i) characterize the maximum a posteriori (MAP) estimates of user identities for the anonymized graph and (ii) provide sufficient conditions for successful de-anonymization for underlying graphs with community structure. Our results generalize prior…
In this paper, a new mathematical formulation for the problem of de-anonymizing social network users by actively querying their membership in social network groups is introduced. In this formulation, the attacker has access to a noisy observation of the group membership of each user in the social network. When an unidentified victim visits a malicious website, the attacker uses browser history sniffing to make queries regarding the victim's social media activity. Particularly, it can make polar queries regarding the victim's group memberships and the victim's identity. The attacker receives no…
A crucial privacy-driven issue nowadays is re-identifying anonymized social networks by mapping them to correlated cross-domain auxiliary networks. Prior works are typically based on modeling social networks as random graphs representing users and their relations, and subsequently quantify the quality of mappings through cost functions that are proposed without sufficient rationale. Also, it remains unknown how to algorithmically meet the demand of such quantifications, i.e., to find the minimizer of the cost functions. We address those concerns in a more realistic social network modeling para…
Recently, graph matching algorithms have been successfully applied to the problem of network de-anonymization, in which nodes (users) participating to more than one social network are identified only by means of the structure of their links to other members. This procedure exploits an initial set of seed nodes large enough to trigger a percolation process which correctly matches almost all other nodes across the different social networks. Our main contribution is to show the crucial role played by clustering, which is a ubiquitous feature of realistic social network graphs (and many other syst…
In recent years there has been a significant increase in the use of graphs as a tool for representing information. It is very important to preserve the privacy of users when one wants to publish this information, especially in the case of social graphs. In this case, it is essential to implement an anonymization process in the data in order to preserve users' privacy. In this paper we present an algorithm for graph anonymization, called Evolutionary Algorithm for Graph Anonymization (EAGA), based on edge modifications to preserve the k-anonymity model.
As an increasing number of social networking data is published and shared for commercial and research purposes, privacy issues about the individuals in social networks have become serious concerns. Vertex identification, which identifies a particular user from a network based on background knowledge such as vertex degree, is one of the most important problems that has been addressed. In reality, however, each individual in a social network is inclined to be associated with not only a vertex identity but also a community identity, which can represent the personal privacy information sensitive t…
The popularity of online social media platforms provides an unprecedented opportunity to study real-world complex networks of interactions. However, releasing this data to researchers and the public comes at the cost of potentially exposing private and sensitive user information. It has been shown that a naive anonymization of a network by removing the identity of the nodes is not sufficient to preserve users' privacy. In order to deal with malicious attacks, k-anonymity solutions have been proposed to partially obfuscate topological information that can be used to infer nodes' identity. In th…
Online users generate tremendous amounts of data. To better serve users, it is required to share the user-related data among researchers, advertisers and application developers. Publishing such data would raise more concerns on user privacy. To encourage data sharing and mitigate user privacy concerns, a number of anonymization and de-anonymization algorithms have been developed to help protect privacy of users. This paper reviews my doctoral research on online users privacy specifically in social media. In particular, I propose a new adversarial attack specialized for social media data. I fur…
Social media users generate tremendous amounts of data. To better serve users, it is required to share the user-related data among researchers, advertisers and application developers. Publishing such data would raise more concerns on user privacy. To encourage data sharing and mitigate user privacy concerns, a number of anonymization and de-anonymization algorithms have been developed to help protect privacy of social media users. In this work, we propose a new adversarial attack specialized for social media data. We further provide a principled way to assess effectiveness of anonymizing diffe…
The increasing popularity of social media has attracted a huge number of people to participate in numerous activities on a daily basis. This results in tremendous amounts of rich user-generated data. This data provides opportunities for researchers and service providers to study and better understand users' behaviors and further improve the quality of the personalized services. Publishing user-generated data risks exposing individuals' privacy. Users privacy in social media is an emerging task and has attracted increasing attention in recent years. These works study privacy issues in social me…
We address the problem of social network de-anonymization when relationships between people are described by scale-free graphs. In particular, we propose a rigorous, asymptotic mathematical analysis of the network de-anonymization problem while capturing the impact of power-law node degree distribution, which is a fundamental and quite ubiquitous feature of many complex systems such as social networks. By applying bootstrap percolation and a novel graph slicing technique, we prove that large inhomogeneities in the node degree lead to a dramatic reduction of the initial set of nodes that must b…
Real social network datasets provide significant benefits for understanding phenomena such as information diffusion or network evolution. Yet the privacy risks raised from sharing real graph datasets, even when stripped of user identity information, are significant. Previous research shows that many graph anonymization techniques fail against existing graph de-anonymization attacks. However, the specific reason for the success of such de-anonymization attacks is yet to be understood. This paper systematically studies the structural properties of real graphs that make them more vulnerable to ma…
This article examines the principles outlined in the General Data Protection Regulation (GDPR) in the context of social network data. We provide both a practical guide to GDPR-compliant social network data processing, covering aspects such as data collection, consent, anonymization and data analysis, and a broader discussion of the problems emerging when the general principles on which the regulation is based are instantiated to this research area.
Social graphs are widely used in research (e.g., epidemiology) and business (e.g., recommender systems). However, sharing these graphs poses privacy risks because they contain sensitive information about individuals. Graph anonymization techniques aim to protect individual users in a graph, while graph de-anonymization aims to re-identify users. The effectiveness of anonymization and de-anonymization algorithms is usually evaluated with privacy metrics. However, it is unclear how strong existing privacy metrics are when they are used in graph privacy. In this paper, we study 26 privacy metrics…
The advent of social networks poses severe threats on user privacy as adversaries can de-anonymize users' identities by mapping them to correlated cross-domain networks. Without ground-truth mapping, prior literature proposes various cost functions in hope of measuring the quality of mappings. However, there is generally a lacking of rationale behind the cost functions, whose minimizer also remains algorithmically unknown. We jointly tackle above concerns under a more practical social network model parameterized by overlapping communities, which, neglected by prior art, can serve as side infor…
Trust among the users of a social network plays a pivotal role in item recommendation, particularly for the cold start users. Due to the sparse nature of these networks, trust information between any two users may not be always available. To infer the missing trust values, one well-known approach is path based trust estimation, which suggests a user to believe all of its neighbors in the network. In this context, we propose two threshold-based heuristics to overcome the limitation of computation for the path based trust inference. It uses the propagation phenomena of trust and decides a thresh…
Recent work has established that large informatics graphs such as social and information networks have non-trivial tree-like structure when viewed at moderate size scales. Here, we present results from the first detailed empirical evaluation of the use of tree decomposition (TD) heuristics for structure identification and extraction in social graphs. Although TDs have historically been used in structural graph theory and scientific computing, we show that---even with existing TD heuristics developed for those very different areas---TD methods can identify interesting structure in a wide range …
Social Media involve many shared items, such as photos, which may concern more than one user. The first challenge we address in this paper is to develop a way for users of such items to take a decision on to whom to share these items. This is not an easy problem, as users' privacy preferences for the same item may conflict, so an approach that just merges in some way the users' privacy preferences may provide unsatisfactory results. We propose a negotiation mechanism for users to agree on a compromise for the conflicts found. The second challenge we address in this paper relates to the exponen…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
How have individuals of social animals in nature evolved to learn from each other, and what would be the optimal strategy for such learning in a specific environment? Here, we address both problems by employing a deep reinforcement learning model to optimize the social learning strategies (SLSs) of agents in a cooperative game in a multi-dimensional landscape. Throughout the training for maximizing the overall payoff, we find that the agent spontaneously learns various concepts of social learning, such as copying, focusing on frequent and well-performing neighbors, self-comparison, and the imp…
The proliferation of Internet-enabled devices and services has led to a shifting balance between digital and analogue aspects of our everyday lives. In the face of this development there is a growing demand for the study of privacy hazards, the potential for unique user de-anonymization and information leakage between the various social media profiles many of us maintain. To enable the structured study of such adversarial effects, this paper presents a dedicated dataset of cross-platform social network personas (i.e., the same person has accounts on multiple platforms). The corpus comprises 85…
We propose a new probabilistic ant-based heuristic (ANTH-LS) for the longest simple cycle problem. This NP-hard problem has numerous real-world applications in complex networks, including efficient construction of graph layouts, analysis of social networks or bioinformatics. Our algorithm is based on reinforcing the probability of traversing the edges, which have not been present in the long cycles found so far. Experimental results are presented for a set of social networks, protein-protein interation networks, network science graphs and DIMACS graphs. For 6 out of our 22 real-world network t…
The problem of influence maximization is to select the most influential individuals in a social network. With the popularity of social network sites, and the development of viral marketing, the importance of the problem has been increased. The influence maximization problem is NP-hard, and therefore, there will not exist a polynomial-time algorithm to solve the problem unless P=NP. Many heuristics are proposed to find a nearly good solution in a shorter time. In this paper, we propose two heuristic algorithms to find good solutions. The heuristics are based on two ideas: (1) vertices of high d…
We report the results of a game-theoretic experiment with human players who solve the problems of increasing complexity by cooperating in groups of increasing size. Our experimental environment is set up to make it complicated for players to use rational calculation for making the cooperative decisions. This environment is directly translated into a computer simulation, from which we extract the collaboration strategy that leads to the maximal attainable score. Based on this, we measure the error that players make when estimating the benefits of collaboration, and find that humans massively un…
Influence Maximization (IM) is the task of determining k optimal influential nodes in a social network to maximize the influence spread using a propagation model. IM is a prominent problem for viral marketing, and helps significantly in social media advertising. However, developing effective algorithms with minimal time complexity for real-world social networks still remains a challenge. While traditional heuristic approaches have been applied for IM, they often result in minimal performance gains over the computationally expensive Greedy-based and Reverse Influence Sampling-based approaches. …
We consider a dynamic model for competition in a social network, where two strategic agents have fixed beliefs and the non-strategic/regular agents adjust their states according to a distributed consensus protocol. We suppose that one strategic agent must identify k+ target agents in the network in order to maximally spread its own opinion and alter the average opinion that eventually emerges. In the literature, this problem is cast as the maximization of a set function and, leveraging on the submodular property, is solved in a greedy manner by solving k+ separate single targeting problems. Ou…
We identify influential early adopters in a social network, where individuals are resource constrained, to maximize the spread of multiple, costly behaviors. A solution to this problem is especially important for viral marketing. The problem of maximizing influence in a social network is challenging since it is computationally intractable. We make three contributions. First, propose a new model of collective behavior that incorporates individual intent, knowledge of neighbors actions and resource constraints. Second, we show that the multiple behavior influence maximization is NP-hard. Further…
Vast amount of multimedia data contains massive and multifarious social information which is used to construct large-scale social networks. In a complex social network, a character should be ideally denoted by one and only one vertex. However, it is pervasive that a character is denoted by two or more vertices with different names, thus it is usually considered as multiple, different characters. This problem causes incorrectness of results in network analysis and mining. The factual challenge is that character uniqueness is hard to correctly confirm due to lots of complicated factors, e.g. nam…
In this paper, we explore the task of gender classification using limited network data with an application to Fotolog. We take a heuristic approach to automating gender inference based on username, followers and network structure. We test our approach on a subset of 100,000 nodes and analyze our results to find that there is a lot of value in these limited information and that there is great promise in further pursuing this approach to classification.
In complex online social networks, it is crucial for a service consumer to extract the trustworthiest way to a target service provider from numerous social trust paths between them. The extraction of the trustworthiest way (namely, optimal social trust path (OSTP)) with multiple end-to-end quality of trust (QoT) constraints has been proved to be NP-Complete. Heuristic algorithms with polynomial and pseudo-polynomial-time complexities are often used to deal with this challenging problem. However, existing solutions cannot guarantee the efficiency of searching, that is, they can hardly avoid obt…
The increased popularity and ubiquitous availability of online social networks and globalised Internet access have affected the way in which people share content. The information that users willingly disclose on these platforms can be used for various purposes, from building consumer models for advertising, to inferring personal, potentially invasive, information. In this work, we use Twitter, Instagram and Foursquare data to convey the idea that the content shared by users, especially when aggregated across platforms, can potentially disclose more information than was originally intended. We …
Viral marketing campaigns seek to recruit the most influential individuals to cover the largest target audience. This can be modeled as the well-studied maximum coverage problem. There is a related problem when the recruited nodes are connected. It is called the maximum connected cover problem. This problem ensures a strong coordination between the influential nodes which are the backbone of the marketing campaign. In this work, we are interested on both of these problems. Most of the related literature assumes knowledge about the topology of the network. Even in that case, the problem is know…
Influence maximization is a problem of finding a small set of highly influential users, also known as seeds, in a social network such that the spread of influence under certain propagation models is maximized. In this paper, we consider time-critical influence maximization, in which one wants to maximize influence spread within a given deadline. Since timing is considered in the optimization, we also extend the Independent Cascade (IC) model and the Linear Threshold (LT) model to incorporate the time delay aspect of influence diffusion among individuals in social networks. We show that time-cr…
This paper studies the feasibility of synthetic data generation for mission-critical applications. The emphasis is on synthetic data generation for anomalous detection in complex social networks. In particular, the development of a heuristic generative model, capable of creating data for anomalous rare activities in complex social networks is sought. To this end, lessons from social and political literature are applied to prototype a novel implementation of the Agent-based Modeling (ABM) framework, based on simple social interactions between agents, for synthetic data generation in the context…
We present NECTAR, a community detection algorithm that generalizes Louvain method's local search heuristic for overlapping community structures. NECTAR chooses dynamically which objective function to optimize based on the network on which it is invoked. Our experimental evaluation on both synthetic benchmark graphs and real-world networks, based on ground-truth communities, shows that NECTAR provides excellent results as compared with state of the art community detection algorithms.
Inria（法国国家信息与自动化研究所）；Univ. Lille（里尔大学）；CNRS（法国国家科学研究中心）；Università degli Studi di Milano（米兰大学）；University of Insubria（因苏布里亚大学）；Aalto University（阿尔托大学）
In the problem of edge sign prediction, we are given a directed graph (representing a social network), and our task is to predict the binary labels of the edges (i.e., the positive or negative nature of the social relationships). Many successful heuristics for this problem are based on the troll-trust features, estimating at each node the fraction of outgoing and incoming positive/negative edges. We show that these heuristics can be understood, and rigorously analyzed, as approximators to the Bayes optimal classifier for a simple probabilistic model of the edge labels. We then show that the ma…
Online social networks are being increasingly used for analyzing various societal phenomena such as epidemiology, information dissemination, marketing and sentiment flow. Popular analysis techniques such as clustering and influential node analysis, require the computation of eigenvectors of the real graph's adjacency matrix. Recent de-anonymization attacks on Netflix and AOL datasets show that an open access to such graphs pose privacy threats. Among the various privacy preserving models, Differential privacy provides the strongest privacy guarantees. In this paper we propose a privacy preserv…
Identifying the most influential individuals can provide invaluable help in developing and deploying effective viral marketing strategies. Previous studies mainly focus on designing efficient algorithms or heuristics to find top-K influential nodes on a given static social network. While, as a matter of fact, real-world social networks keep evolving over time and a recalculation upon the changed network inevitably leads to a long running time, significantly affecting the efficiency. In this paper, we observe from real-world traces that the evolution of social network follows the preferential a…
Reliable propagation of information through large networks, e.g., communication networks, social networks or sensor networks is very important in many applications concerning marketing, social networks, and wireless sensor networks. However, social ties of friendship may be obsolete, and communication links may fail, inducing the notion of uncertainty in such networks. In this paper, we address the problem of optimizing information propagation in uncertain networks given a constrained budget of edges. We show that this problem requires to solve two NP-hard subproblems: the computation of expec…
