Hide and Seek: Outwitting Community Detection Algorithms

Mittal, Shravika; Sengupta, Debarka; Chakraborty, Tanmoy

doi:10.1109/tcss.2021.3062711

Cited by 34 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As evaluation metrics, we consider three measures: modularity (M), coverage (C), and partition quality (PQ). In the experiments, we set B = 0.3|V C |, i.e., 30% of the size of the target community C as in [9]. As result, in Table I, we obtain three evaluation results for two real-world graphs, we see that there is an increase in most evaluation metrics for each graph G ′′ compared to those of G ′ .…”

Section: Numerical and Simulation Resultsmentioning

confidence: 95%

“…In this paper, as a measure of community structure in the graph, we use what is called permanence proposed by Algorithm 1: NEURAL [9] Input: Graph G, Target community C, Budget B > 0 Output: Updated graph G ′ 1 P l,ad = 0 and P l,de = 0; 2 while B > 0 do 3 Step1: For u ∈ C and v ∈ C ′ , where C ′ is the community of maximum external pull for u, set G ′ to be the graph with added edge (u, v). Compute P erm(u, G) and P erm(u, G ′ ) and choose the best edge satisfying:…”

Section: B Permanencementioning

confidence: 99%

“…For community deception, the authors [9] proposed Network Deception Using Permanence Loss (NEURAL) algorithm in their work. The main idea of the algorithm is that some intracommunity or inter-community edges are updated (added or deleted) based on the permanence difference between before the update and after the edge update.…”

Section: Community Deception Algorithm -Neural [9]mentioning

confidence: 99%

“…The main idea of the algorithm is that some intracommunity or inter-community edges are updated (added or deleted) based on the permanence difference between before the update and after the edge update. To see this more precisely, we first define a permanence loss [9] of two graphs G and G ′ , where G ′ is the graph result from some edge update on G, as follows:…”

Section: Community Deception Algorithm -Neural [9]mentioning

confidence: 99%

“…Unlike the community detection approaches so far, the authors in [9] conducted a study that could well hide the community structure in the graph. They proposed a community deception algorithm named NEURAL, which is a method of selecting a specific edge in the graph based on this permanence score and adding or deleting it to intracommunity or intercommunity.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Permanence based Hidden Community and Graph Recovery in Social Networks

Choi¹,

Sim²

2023

Preprint

View full text Add to dashboard Cite

Due to the recent development of data analysis techniques, technologies for detecting communities through information expressed in social networks have been developed. Although it has several advantages, including the ability to effectively share recommended items through an estimated community, it may cause personal privacy issues. Therefore, recently, the problem of hiding the real community well is being studied at the same time. As an example, Mittal et al., proposed an algorithm called NEURAL that can hide this community well based on a metric called permanence. Based on this, in this study, we propose a Reverse NEURAL (R-NEURAL) algorithm that restores the community as well as the original graph structure using permanence. The proposed algorithm includes a method for well restoring not only the community hidden by the NEURAL algorithm but also the original graph structure modified by recovered edges. We conduct experiments on real-world graphs and found that the proposed algorithm recovers well the hidden community as well as the graph structure.

show abstract

Section: Numerical and Simulation Resultsmentioning

confidence: 95%

Section: B Permanencementioning

confidence: 99%

Section: Community Deception Algorithm -Neural [9]mentioning

confidence: 99%

Section: Community Deception Algorithm -Neural [9]mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations