Adversarial Attack on Community Detection by Hiding Individuals

Li, Jia; Zhang, Honglei; Han, Zhichao; Rong, Yu; Cheng, Hong; Huang, Junzhou

doi:10.1145/3366423.3380171

Cited by 68 publications

(33 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu et al [22] introduce integrated gradients that could guide the attack of perturbing certain features or edges while still benefiting from the parallel computations. Additionally, several heuristic methods are also proposed to poison the GNNs [1,8,16], revealing the vulnerability of GNNs in different graph analysis tasks. However, the adversarial patterns of attacks are less explored and the reasons of the success of attacks still remain unclear.…”

Section: Related Workmentioning

confidence: 99%

Deep Insights into Graph Adversarial Learning: An Empirical Study Perspective

Peng

et al. 2021

Human Brain and Artificial Intelligence

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have shown to be vulnerable against adversarial examples in many works, which encourages researchers to drop substantial attention to its robustness and security. However, so far, the reasons for the success of adversarial attacks and the intrinsic vulnerability of GNNs still remain unclear. The work presented here outlines an empirical study to further investigate these observations and provide several insights. Experimental results, analyzed across a variety of benchmark GNNs on two datasets, indicate that GNNs are indeed sensitive to adversarial attacks due to its non-robust message functions. To exploit the adversarial patterns, we introduce two measurements to depict the randomness of node labels and features for a graph, noticing that the neighborhood entropy significantly increased under adversarial attacks. Furthermore, we find out that the adversarially manipulated graphs typically tend to be much denser and high-rank, where most of the dissimilar nodes are intentionally linked. And the stronger the attacks are, such as Metattack, the patterns are more apparent. To sum up, our findings shed light on understanding adversarial attacks on graph data and lead potential advancement in enhancing the robustness of GNNs.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Insights into Graph Adversarial Learning: An Empirical Study Perspective

Peng

et al. 2021

Human Brain and Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…The community detection algorithms (CDAs) have been designed to unveil some essential insights, such as human interactions in social networks, 9,10 subject descriptions in information networks, 11,12 interaction between neurons, 13 the association among terrorists in the criminal network, 14,15 and so forth. Community identification tools raise multiple considerable privacy concerns.…”

Section: Introductionmentioning

confidence: 99%

“…They provided a residual entropy minimization formula for the deception of community structure in the network. Li et al 9 aimed to hide targeted nodes from the CDAs using the black‐box approach. They claimed that the generated adversarial graphs through their proposed approach can be transferred to other learning‐based community detection models.…”

Section: Introductionmentioning

confidence: 99%

Intelligent deception techniques against adversarial attack on the industrial system

Kumari¹,

Yadav²,

Namasudra

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Community detection algorithms (CDAs) are aiming to group nodes based on their connections and play an essential role in the complex system analysis. However, for privacy reasons, we may want to prevent communities or a group of nodes in the complex industrial network from being discovered in some instances, leading to the topics on community deception. In this paper, we introduce and formalize two intelligent community deception methods to conceal the nodes from various CDAs. We used node‐based matrices, persistence and safeness scores, to formalize the optimization problems to confound the CDAs. The persistence score is used to destabilize the constant communities in the network while the safeness score is used to assess the level of hiding of a node from CDAs. The objective functions aim to minimize the persistence score and maximize the safeness score of the nodes in the network. From the simulation results, it can be analyzed that the proposed strategies are intelligently concealing the community information in the complex industrial system.

show abstract

“…From a Deep Graph Kernels framework that can learn latent representations inside a graph 24 or a variant of a convolutional network that encodes the local graph structure and the features of nodes 25 . Up to adversarial networks that make perturbations on the graph to generate constrained ones which are then classified into communities 26 or the extraction of temporal features using local long short-term memory networks to be used to learn spatio-temporal patterns to infer the communities 27 . Finally, the Graph Attention Networks provide a methodology based on convolutional networks, without depending or knowing the graph structure upfront 28 .…”

Section: Introductionmentioning

confidence: 99%

Community detection‐based deep neural network architectures: A fully automated framework based on Likert‐scale data

Pérez‐Benito

García‐Gómez

Navarro‐Pardo

et al. 2020

Math Methods in App Sciences

View full text Add to dashboard Cite

Deep Neural Networks have emerged as a state-of-the-art tool in very different research fields due to its adaptive power to the decision space since they do not presuppose any linear relationship between data. Some of the main disadvantages of these trending models are that the choice of the network underlying architecture profoundly influences the performance of the model and that the architecture design requires prior knowledge of the field of study.The use of questionnaires is hugely extended in social/behavioral sciences. The main contribution of this work is to automate the process of a deep neural network architecture design by using an agglomerative hierarchical algorithm that mimics the conceptual structure of such surveys. Although the train had regression purposes, it is easily convertible to deal with classification tasks.Our proposed methodology will be tested with a database containing sociodemographic data and the responses to five psychometric Likert scales related to the prediction of happiness. These scales have been already used to design a DNN architecture based on the subdimension of the scales. We show that our new network configurations outperform the previous existing DNN architectures.

show abstract

Adversarial Attack on Community Detection by Hiding Individuals

Cited by 68 publications

References 25 publications

Deep Insights into Graph Adversarial Learning: An Empirical Study Perspective

Deep Insights into Graph Adversarial Learning: An Empirical Study Perspective

Intelligent deception techniques against adversarial attack on the industrial system

Community detection‐based deep neural network architectures: A fully automated framework based on Likert‐scale data

Contact Info

Product

Resources

About