AddGraph: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN

Zheng, Li; Li, Zhenpeng; Li, Jian; Li, Zhao; Gao, Jun

doi:10.24963/ijcai.2019/614

Cited by 172 publications

(118 citation statements)

References 4 publications

Supporting

Mentioning

118

Contrasting

Order By: Relevance

“…FGSS has ideal graphical scales over researches [43] and [39], hence it could recognize anomalous samples in HD spaces. Moreover, the author [85] proposed AddGraph to distinguish (8) SOD R(p) (p) = distance(Pointo, HyperPlan(R(p)))∕v R(p) 1 , the anomalous users that create counterfeit information to accomplish the potential gain. The GAD model detects the long-term and short-term anomalous patterns of fake data using dynamic graphs.…”

Section: High Dimensional Sub-space Based Techniquesmentioning

confidence: 99%

Group Anomaly Detection: Past Notions, Present Insights, and Future Prospects

et al. 2021

View full text Add to dashboard Cite

Anomaly detection has evolved as a successful research subject in the areas such as bibliometrics, informatics and computer networks including security-based and social networks. Almost all existing anomaly detection techniques have some limitations and do not focus specifically on detecting anomalous groups. Anomaly detection is also a crucial problem in processing large-scale datasets when our goal is to find abnormal values or unusual events. The authors decided to survey existing group anomaly detection techniques because there is a need to consider group anomalies for mitigation of risks, prevention of malicious collaborative activities, and other interesting explanatory insights by identifying groups that are not consistent with regular group patterns. In this research, we bifurcated group anomaly detection techniques into activity-based and graph-based methods. The graphical methodologies are then further classified under static versus dynamic and attributed versus plain graph methods. We have also listed the datasets used in various studies to detect group anomalies along with detected anomalies and the various performance measures used to validate the results. Towards the end, we have provided various applications of group anomaly detection and the research challenges that group anomaly detection presents to the scientific community and enlisted some of the future trends for this particular research area.

show abstract

Section: High Dimensional Sub-space Based Techniquesmentioning

confidence: 99%

Group Anomaly Detection: Past Notions, Present Insights, and Future Prospects

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Dynamic graph anomaly detection was performed in [62], where an Attentionbased temporal Graph Convolutional Network (GCN) model was developed. In this study, anomalous edges of the graph were identified utilizing temporal features as the long and short term patterns occurring within dynamic graphs.…”

Section: Graph-based Approachesmentioning

confidence: 99%

A graph neural network method for distributed anomaly detection in IoT

et al. 2020

View full text Add to dashboard Cite

Recent IoT proliferation has undeniably affected the way organizational activities and business procedures take place within several IoT domains such as smart manufacturing, food supply chain, intelligent transportation systems, medical care infrastructures etc. The number of the interconnected edge devices has dramatically increased, creating a huge volume of transferred data susceptible to leakage, modification or disruption, ultimately affecting the security level, robustness and QoS of the attacked IoT ecosystem. In an attempt to prevent or mitigate network abnormalities while accommodating the cohesiveness among the involved entities, modeling their interrelations and incorporating their structural, content and temporal attributes, graph-based anomaly detection solutions have been repeatedly adopted. In this article we propose, a multi-agent system, with each agent implementing a Graph Neural Network, in order to exploit the collaborative and cooperative nature of intelligent agents for anomaly detection. To this end, against the propagating nature of cyber-attacks such as the Distributed Denial-of-Service (DDoS), we propose a distributed detection scheme, which aims to monitor efficiently

show abstract

“…We use an adjacency matrix A t ∈ R n×n to represent edges in E t where n = |V t |. Similar to [24,27,47,50], the number of nodes in the graph is assumed to be constant across all timestamps (thus maintaining the shape of the adjacency matrix A t ). However, our method is also applicable to real world networks where the number of active nodes fluctuates from one snapshot to another.…”

Section: Problem Definition 31 Dynamic Graphmentioning

confidence: 99%

Laplacian Change Point Detection for Dynamic Graphs

Huang

Hitti

Rabusseau

et al. 2020

Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Dynamic and temporal graphs are rich data structures that are used to model complex relationships between entities over time. In particular, anomaly detection in temporal graphs is crucial for many real world applications such as intrusion identification in network systems, detection of ecosystem disturbances and detection of epidemic outbreaks. In this paper, we focus on change point detection in dynamic graphs and address two main challenges associated with this problem: I) how to compare graph snapshots across time, II) how to capture temporal dependencies. To solve the above challenges, we propose Laplacian Anomaly Detection (LAD) which uses the spectrum of the Laplacian matrix of the graph structure at each snapshot to obtain low dimensional embeddings. LAD explicitly models short term and long term dependencies by applying two sliding windows. In synthetic experiments, LAD outperforms the state-of-the-art method. We also evaluate our method on three real dynamic networks: UCI message network, US senate co-sponsorship network and Canadian bill voting network. In all three datasets, we demonstrate that our method can more effectively identify anomalous time points according to significant real world events. CCS CONCEPTS • Computing methodologies → Anomaly detection; Temporal reasoning; Spectral methods; • Mathematics of computing → Spectra of graphs; • Theory of computation → Dynamic graph algorithms.

show abstract

AddGraph: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN

Cited by 172 publications

References 4 publications

Group Anomaly Detection: Past Notions, Present Insights, and Future Prospects

Group Anomaly Detection: Past Notions, Present Insights, and Future Prospects

A graph neural network method for distributed anomaly detection in IoT

Laplacian Change Point Detection for Dynamic Graphs

Contact Info

Product

Resources

About