Temporal Graph Mining for Anomaly Detection

用于异常检测的时间图挖掘

• 批准号: DP240101547
• 负责人: Prof Shirui Pan
• 金额: $ 32.98万
• 依托单位: Griffith University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2024
• 资助国家: 澳大利亚
• 起止时间: 2024-01-01 至 2026-12-31
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP240101547
• 关键词: Temporal; Graph; Mining; Anomaly; Detection

This project aims to develop new technologies to detect anomalous patterns from dynamic networked data. Anomalies in networked data are commonly seen but are often hidden within the complex interconnections of large-scale, heterogeneous, and dynamic data, rendering existing detection methods ineffective. This project expects to design novel temporal graph mining techniques to compress large-scale networks, unify heterogeneous information, and enable label-efficient anomaly detection. The performance will be assessed in social and business networks, with significant benefits to governments and businesses in many critical applications, including cyberbullying detection, malicious account detection, and cyber-attack detection.

该项目旨在开发从动态网络数据中检测异常模式的新技术。网络数据中的异常是常见的，但往往隐藏在大规模、异构和动态数据的复杂互连中，使得现有的检测方法无效。该项目期望设计新颖的时间图挖掘技术来压缩大规模网络，统一异构信息，并实现标签高效的异常检测。该性能将在社交和商业网络中进行评估，在许多关键应用中为政府和企业带来重大好处，包括网络欺凌检测、恶意账户检测和网络攻击检测。