Hiding individuals and communities in a social network

Abstract

The Internet and social media have fueled enormous interest in social network analysis. New tools continue to be developed and used to analyse our personal connections, with particular emphasis on detecting communities or identifying key individuals in a social network. This raises privacy concerns that are likely to exacerbate in the future. With this in mind, we ask the question: Can individuals or groups actively manage their connections to evade social network analysis tools? By addressing this question, the general public may better protect their privacy, oppressed activist groups may better conceal their existence, and security agencies may better understand how terrorists escape detection. We first study how an individual can evade "network centrality" analysis without compromising his or her influence within the network. We prove that an optimal solution to this problem is hard to compute. Despite this hardness, we demonstrate that even a simple heuristic, whereby attention is restricted to the individual's immediate neighbourhood, can be surprisingly effective in practice. For instance, it could disguise Mohamed Atta's leading position within the WTC terrorist network, and that is by rewiring a strikingly-small number of connections. Next, we study how a community can increase the likelihood of being overlooked by community-detection algorithms. We propose a measure of concealment, expressing how well a community is hidden, and use it to demonstrate the effectiveness of a simple heuristic, whereby members of the community either "unfriend" certain other members, or "befriend" some non-members, in a coordinated effort to camouflage their community.

Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing

“…In particular, ||δ || 0 is the number of edges added or removed by the attacker. Two attacks: An attacker can manipulate the detected communities via adversarial structural perturbation [8,9,13,28,36]. Specifically, there are two types of attacks to community detection:…”

“…However, multiple recent studies showed that community detection is vulnerable to adversarial structural perturbations [8,9,13,28,36]. Specifically, via adding or removing a small number of carefully selected edges in a graph, an attacker can manipulate the detected communities.…”

Your Stance is Exposed! Analysing Possible Factors for Stance Detection on Social Media

“…We believe that our findings in this study raises a large concern about protecting the privacy of social media users, where their beliefs and leanings could be easily predicted using any of the footprint signals they leave online. This should motivate social media networks owners and designers to develop methods for protecting the privacy of their users [51].…”

Towards an Efficient and General Framework of Robust Training for Graph Neural Networks

“…Therefore, in the following experiments we set n = 0.05N . We compare our GTA and ZO-GTA methods with DICE ('delete edges internally, connect externally) [20], CE-PGD and CW-PGD [13]. We follow the hyper parameters and experimental settings as given in in [13] for a fair comparison.…”