Attack Tolerance of Link Prediction Algorithms: How to Hide Your Relations in a Social Network

Waniek, Marcin; Zhou, Kai; Vorobeychik, Yevgeniy; Moro, Esteban; Michalak, Tomasz P.; Rahwan, Talal

doi:10.48550/arxiv.1809.00152

Cited by 2 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fionda et al propose a novel community deception method based on the safeness [47]. In link prediction, Waniek et al propose two strategies called closed-triad-removal and open-triad-creation [48], which solve the privacy problem caused by link prediction methods. Zhou et al propose a method to attack local similarity and global similarity by deleting edges [49].…”

Section: Graph Attack Methodsmentioning

confidence: 99%

Graphfool: Targeted Label Adversarial Attack on Graph Embedding

Chen¹,

Lin²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep learning is effective in graph analysis. It is widely applied in many related areas, such as link prediction, node classification, community detection, and graph classification etc. Graph embedding, which learns low-dimensional representations for vertices or edges in the graph, usually employs deep models to derive the embedding vector. However, these models are vulnerable. We envision that graph embedding methods based on deep models can be easily attacked using adversarial examples. Thus, in this paper, we propose Graphfool, a novel targeted label adversarial attack on graph embedding. It can generate adversarial graph to attack graph embedding methods via classifying boundary and gradient information in graph convolutional network (GCN). Specifically, we perform the following steps: 1),We first estimate the classification boundaries of different classes. 2), We calculate the minimal perturbation matrix to misclassify the attacked vertex according to the target classification boundary. 3), We modify the adjacency matrix according to the maximal absolute value of the disturbance matrix. This process is implemented iteratively. To the best of our knowledge, this is the first targeted label attack technique. The experiments on real-world graph networks demonstrate that Graphfool can derive better performance than state-of-art techniques. Compared with the second best algorithm, Graphfool can achieve an average improvement of 11.44% in attack success rate.

show abstract

Section: Graph Attack Methodsmentioning

confidence: 99%

Graphfool: Targeted Label Adversarial Attack on Graph Embedding

Chen¹,

Lin²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Link-relevant task Link prediction is another fundamental research problems in network analysis. In this scenario, [68] studies the link connections, and propose heuristic algorithms to evade the detection by rewiring operations. Furthermore, [9] puts forward a novel iterative gradient attack method based on a graph auto-encoder framework.…”

Section: Major Contributionsmentioning

confidence: 99%

A Survey of Adversarial Learning on Graphs

Chen¹,

Li²,

Peng

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep learning models on graphs have achieved remarkable performance in various graph analysis tasks, e.g., node classification, link prediction and graph clustering. However, they expose uncertainty and unreliability against the well-designed inputs, i.e., adversarial examples. Accordingly, various studies have emerged for both attack and defense addressed in different graph analysis tasks, leading to the arms race in graph adversarial learning. For instance, the attacker has poisoning and evasion attack, and the defense group correspondingly has preprocessing-and adversarial-based methods. Despite the booming works, there still lacks a unified problem definition and a comprehensive review. To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically. Specifically, we survey and unify the existing works w.r.t. attack and defense in graph analysis tasks, and give proper definitions and taxonomies at the same time. Besides, we emphasize the importance of related evaluation metrics, and investigate and summarize them comprehensively. Hopefully, our works can serve as a reference for the relevant researchers, thus providing assistance for their studies. More details of our works are available at https://github.com/gitgiter/Graph-Adversarial-Learning.

show abstract

Attack Tolerance of Link Prediction Algorithms: How to Hide Your Relations in a Social Network

Cited by 2 publications

References 28 publications

Graphfool: Targeted Label Adversarial Attack on Graph Embedding

Graphfool: Targeted Label Adversarial Attack on Graph Embedding

A Survey of Adversarial Learning on Graphs

Contact Info

Product

Resources

About