Alert button
Picture for Kai Zhou

Kai Zhou

Alert button

Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach

Aug 02, 2023
Xing Ai, Jialong Zhou, Yulin Zhu, Gaolei Li, Tomasz P. Michalak, Xiapu Luo, Kai Zhou

Figure 1 for Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach
Figure 2 for Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach
Figure 3 for Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach
Figure 4 for Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach

Graph anomaly detection (GAD) has achieved success and has been widely applied in various domains, such as fraud detection, cybersecurity, finance security, and biochemistry. However, existing graph anomaly detection algorithms focus on distinguishing individual entities (nodes or graphs) and overlook the possibility of anomalous groups within the graph. To address this limitation, this paper introduces a novel unsupervised framework for a new task called Group-level Graph Anomaly Detection (Gr-GAD). The proposed framework first employs a variant of Graph AutoEncoder (GAE) to locate anchor nodes that belong to potential anomaly groups by capturing long-range inconsistencies. Subsequently, group sampling is employed to sample candidate groups, which are then fed into the proposed Topology Pattern-based Graph Contrastive Learning (TPGCL) method. TPGCL utilizes the topology patterns of groups as clues to generate embeddings for each candidate group and thus distinct anomaly groups. The experimental results on both real-world and synthetic datasets demonstrate that the proposed framework shows superior performance in identifying and localizing anomaly groups, highlighting it as a promising solution for Gr-GAD. Datasets and codes of the proposed framework are at the github repository https://anonymous.4open.science/r/Topology-Pattern-Enhanced-Unsupervised-Group-level-Graph-Anomaly-Detection.

Viaarxiv icon

Dual-Space Attacks against Random-Walk-based Anomaly Detection

Jul 26, 2023
Yuni Lai, Marcin Waniek, Yulin Zhu, Liying Li, Jingwen Wu, Tomasz P. Michalak, Talal Rahwan, Kai Zhou

Figure 1 for Dual-Space Attacks against Random-Walk-based Anomaly Detection
Figure 2 for Dual-Space Attacks against Random-Walk-based Anomaly Detection
Figure 3 for Dual-Space Attacks against Random-Walk-based Anomaly Detection
Figure 4 for Dual-Space Attacks against Random-Walk-based Anomaly Detection

Random Walks-based Anomaly Detection (RWAD) is commonly used to identify anomalous patterns in various applications. An intriguing characteristic of RWAD is that the input graph can either be pre-existing or constructed from raw features. Consequently, there are two potential attack surfaces against RWAD: graph-space attacks and feature-space attacks. In this paper, we explore this vulnerability by designing practical dual-space attacks, investigating the interplay between graph-space and feature-space attacks. To this end, we conduct a thorough complexity analysis, proving that attacking RWAD is NP-hard. Then, we proceed to formulate the graph-space attack as a bi-level optimization problem and propose two strategies to solve it: alternative iteration (alterI-attack) or utilizing the closed-form solution of the random walk model (cf-attack). Finally, we utilize the results from the graph-space attacks as guidance to design more powerful feature-space attacks (i.e., graph-guided attacks). Comprehensive experiments demonstrate that our proposed attacks are effective in enabling the target nodes from RWAD with a limited attack budget. In addition, we conduct transfer attack experiments in a black-box setting, which show that our feature attack significantly decreases the anomaly scores of target nodes. Our study opens the door to studying the dual-space attack against graph anomaly detection in which the graph space relies on the feature space.

* 13 pages 
Viaarxiv icon

Homophily-Driven Sanitation View for Robust Graph Contrastive Learning

Jul 24, 2023
Yulin Zhu, Xing Ai, Yevgeniy Vorobeychik, Kai Zhou

Figure 1 for Homophily-Driven Sanitation View for Robust Graph Contrastive Learning
Figure 2 for Homophily-Driven Sanitation View for Robust Graph Contrastive Learning
Figure 3 for Homophily-Driven Sanitation View for Robust Graph Contrastive Learning
Figure 4 for Homophily-Driven Sanitation View for Robust Graph Contrastive Learning

We investigate adversarial robustness of unsupervised Graph Contrastive Learning (GCL) against structural attacks. First, we provide a comprehensive empirical and theoretical analysis of existing attacks, revealing how and why they downgrade the performance of GCL. Inspired by our analytic results, we present a robust GCL framework that integrates a homophily-driven sanitation view, which can be learned jointly with contrastive learning. A key challenge this poses, however, is the non-differentiable nature of the sanitation objective. To address this challenge, we propose a series of techniques to enable gradient-based end-to-end robust GCL. Moreover, we develop a fully unsupervised hyperparameter tuning method which, unlike prior approaches, does not require knowledge of node labels. We conduct extensive experiments to evaluate the performance of our proposed model, GCHS (Graph Contrastive Learning with Homophily-driven Sanitation View), against two state of the art structural attacks on GCL. Our results demonstrate that GCHS consistently outperforms all state of the art baselines in terms of the quality of generated node embeddings as well as performance on two important downstream tasks.

Viaarxiv icon

Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks

Feb 20, 2023
Shuai Han, Lukas Stelz, Horst Stoecker, Lingxiao Wang, Kai Zhou

Figure 1 for Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks
Figure 2 for Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks
Figure 3 for Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks
Figure 4 for Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks

A physics-informed neural network (PINN) embedded with the susceptible-infected-removed (SIR) model is devised to understand the temporal evolution dynamics of infectious diseases. Firstly, the effectiveness of this approach is demonstrated on synthetic data as generated from the numerical solution of the susceptible-asymptomatic-infected-recovered-dead (SAIRD) model. Then, the method is applied to COVID-19 data reported for Germany and shows that it can accurately identify and predict virus spread trends. The results indicate that an incomplete physics-informed model can approach more complicated dynamics efficiently. Thus, the present work demonstrates the high potential of using machine learning methods, e.g., PINNs, to study and predict epidemic dynamics in combination with compartmental models.

* 23 pages, 14 figures 
Viaarxiv icon

Simple yet Effective Gradient-Free Graph Convolutional Networks

Feb 01, 2023
Yulin Zhu, Xing Ai, Qimai Li, Xiao-Ming Wu, Kai Zhou

Figure 1 for Simple yet Effective Gradient-Free Graph Convolutional Networks
Figure 2 for Simple yet Effective Gradient-Free Graph Convolutional Networks
Figure 3 for Simple yet Effective Gradient-Free Graph Convolutional Networks
Figure 4 for Simple yet Effective Gradient-Free Graph Convolutional Networks

Linearized Graph Neural Networks (GNNs) have attracted great attention in recent years for graph representation learning. Compared with nonlinear Graph Neural Network (GNN) models, linearized GNNs are much more time-efficient and can achieve comparable performances on typical downstream tasks such as node classification. Although some linearized GNN variants are purposely crafted to mitigate ``over-smoothing", empirical studies demonstrate that they still somehow suffer from this issue. In this paper, we instead relate over-smoothing with the vanishing gradient phenomenon and craft a gradient-free training framework to achieve more efficient and effective linearized GNNs which can significantly overcome over-smoothing and enhance the generalization of the model. The experimental results demonstrate that our methods achieve better and more stable performances on node classification tasks with varying depths and cost much less training time.

Viaarxiv icon

How Fraudster Detection Contributes to Robust Recommendation

Nov 22, 2022
Yuni Lai, Kai Zhou

Figure 1 for How Fraudster Detection Contributes to Robust Recommendation
Figure 2 for How Fraudster Detection Contributes to Robust Recommendation
Figure 3 for How Fraudster Detection Contributes to Robust Recommendation
Figure 4 for How Fraudster Detection Contributes to Robust Recommendation

The adversarial robustness of recommendation systems under node injection attacks has received considerable research attention. Recently, a robust recommendation system GraphRfi was proposed, and it was shown that GraphRfi could successfully mitigate the effects of injected fake users in the system. Unfortunately, we demonstrate that GraphRfi is still vulnerable to attacks due to the supervised nature of its fraudster detection component. Specifically, we propose a new attack metaC against GraphRfi, and further analyze why GraphRfi fails under such an attack. Based on the insights we obtained from the vulnerability analysis, we build a new robust recommendation system PDR by re-designing the fraudster detection component. Comprehensive experiments show that our defense approach outperforms other benchmark methods under attacks. Overall, our research demonstrates an effective framework of integrating fraudster detection into recommendation to achieve adversarial robustness.

Viaarxiv icon

FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification

Oct 25, 2022
Yulin Zhu, Liang Tong, Kai Zhou

Figure 1 for FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification
Figure 2 for FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification
Figure 3 for FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification
Figure 4 for FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification

Recently, a lot of research attention has been devoted to exploring Web security, a most representative topic is the adversarial robustness of graph mining algorithms. Especially, a widely deployed adversarial attacks formulation is the graph manipulation attacks by modifying the relational data to mislead the Graph Neural Networks' (GNNs) predictions. Naturally, an intrinsic question one would ask is whether we can accurately identify the manipulations over graphs - we term this problem as poisoned graph sanitation. In this paper, we present FocusedCleaner, a poisoned graph sanitation framework consisting of two modules: bi-level structural learning and victim node detection. In particular, the structural learning module will reserve the attack process to steadily sanitize the graph while the detection module provides the "focus" - a narrowed and more accurate search region - to structural learning. These two modules will operate in iterations and reinforce each other to sanitize a poisoned graph step by step. Extensive experiments demonstrate that FocusedCleaner outperforms the state-of-the-art baselines both on poisoned graph sanitation and improving robustness.

Viaarxiv icon

SMTNet: Hierarchical cavitation intensity recognition based on sub-main transfer network

Mar 23, 2022
Yu Sha, Johannes Faber, Shuiping Gou, Bo Liu, Wei Li, Stefan Schramm, Horst Stoecker, Thomas Steckenreiter, Domagoj Vnucec, Nadine Wetzstein, Andreas Widl, Kai Zhou

Figure 1 for SMTNet: Hierarchical cavitation intensity recognition based on sub-main transfer network
Figure 2 for SMTNet: Hierarchical cavitation intensity recognition based on sub-main transfer network
Figure 3 for SMTNet: Hierarchical cavitation intensity recognition based on sub-main transfer network
Figure 4 for SMTNet: Hierarchical cavitation intensity recognition based on sub-main transfer network

With the rapid development of smart manufacturing, data-driven machinery health management has been of growing attention. In situations where some classes are more difficult to be distinguished compared to others and where classes might be organised in a hierarchy of categories, current DL methods can not work well. In this study, a novel hierarchical cavitation intensity recognition framework using Sub-Main Transfer Network, termed SMTNet, is proposed to classify acoustic signals of valve cavitation. SMTNet model outputs multiple predictions ordered from coarse to fine along a network corresponding to a hierarchy of target cavitation states. Firstly, a data augmentation method based on Sliding Window with Fast Fourier Transform (Swin-FFT) is developed to solve few-shot problem. Secondly, a 1-D double hierarchical residual block (1-D DHRB) is presented to capture sensitive features of the frequency domain valve acoustic signals. Thirdly, hierarchical multi-label tree is proposed to assist the embedding of the semantic structure of target cavitation states into SMTNet. Fourthly, experience filtering mechanism is proposed to fully learn a prior knowledge of cavitation detection model. Finally, SMTNet has been evaluated on two cavitation datasets without noise (Dataset 1 and Dataset 2), and one cavitation dataset with real noise (Dataset 3) provided by SAMSON AG (Frankfurt). The prediction accurcies of SMTNet for cavitation intensity recognition are as high as 95.32%, 97.16% and 100%, respectively. At the same time, the testing accuracies of SMTNet for cavitation detection are as high as 97.02%, 97.64% and 100%. In addition, SMTNet has also been tested for different frequencies of samples and has achieved excellent results of the highest frequency of samples of mobile phones.

* arXiv admin note: substantial text overlap with arXiv:2203.01118; text overlap with arXiv:2202.13226 
Viaarxiv icon