De-Anonymizing Social Networks With Overlapping Community Structure

Abstract

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 information for de-anonymization. Regarding the unavailability of groundtruth mapping to adversaries, by virtue of the Minimum Mean Square Error (MMSE), our first contribution is a well-justified cost function minimizing the expected number of mismatched users over all possible true mappings. While proving the NPhardness of minimizing MMSE, we validly transform it into the weighted-edge matching problem (WEMP), which, as disclosed theoretically, resolves the tension between optimality and complexity: (i) WEMP asymptotically returns a negligible mapping error in large network size under mild conditions facilitated by higher overlapping strength; (ii) WEMP can be algorithmically characterized via the convex-concave based de-anonymization algorithm (CBDA), perfectly finding the optimum of WEMP. Extensive experiments further confirm the effectiveness of CBDA under overlapping communities, in terms of averagely 90% reidentified users in the rare true cross-domain co-author networks when communities overlap densely, and roughly 70% enhanced re-identification ratio compared to non-overlapping cases.

A Comprehensive Analysis of Privacy-Preserving Solutions Developed for Online Social Networks

“…Recently, many de-anonymization methods have been proposed, and some methods have accuracies of over 80% in correctly identifying nodes from G [259]. Recently, due to rapid developments in digitization, the availability of personal information on various OSNs is rising rapidly, leading to a variety of privacy problems [260][261][262][263][264][265]. These developments indicate the eve-increasing interest of researchers in de-anonymization rather than anonymization.…”

A survey on email visualisation research to address the conflict between privacy and access

“…However, the issue is that, because much of the data remains unaltered, privacy management of this kind can be bypassed to reveal private information. Pseudonymisation and anonymisation in particular have been shown to be an ineffective, 'naive' (Task 2015) method of privacy preservation, particularly with reference to social network data Backstrom et al 2007;Ma et al 2017;Wang et al 2018;Fu et al 2020;. Additionally, the reliance upon the skill and knowledge of the person applying the privacy management strategy means that 'human judgement becomes a strong factor' (Kaczmarek and West 2018) which is another key reason why the level of protection offered by this approach is so low.…”

Seed-free Graph De-anonymiztiation with Adversarial Learning

“…Before conducting the experiments, we add perturbation to anonymize the original graphs. We randomly remove fraction of edges from the original graphs to respectively generate and , which is commonly used in the previous works [8,17,26]. Note that by doing so, the number of the edges overlapped between and is (1 − ) 2 (e.g., if =0.5, 25% edges in the original graph overlap between and ).…”

“…Beside structure of graphs, many works utilize the other information as side information to enhance the performance of graph deanonymization, such as community [8,27], attributes [17], semantics [29,30]. However, these methods also face the problem that a large amount of prior information might be difficult to obtain.…”