Anonymized Network Sensing Graph Challenge

2024-09-12

IEEE Conference on High Performance Extreme Computing

AI Summary

This study addresses the dual challenges of network anomaly detection and privacy preservation in large-scale, open collaborative environments—particularly for sparse, anonymized graph-structured data from social media, sensor networks, and scientific datasets. To overcome modeling and sharing difficulties, we introduce the first standardized, anonymized source–destination traffic matrix dataset, constructed from over 100 billion packets captured by the CAIDA global Internet telescope. Methodologically, we integrate GraphBLAS-based graph computation, sparse traffic matrix modeling, differential-privacy-inspired anonymization, and structured graph analysis. Our key contribution is a reproducible, scalable benchmarking framework for anonymized traffic graph analysis that simultaneously ensures high fidelity and strong privacy guarantees, enabling secure cross-institutional collaborative modeling. The framework has already attracted diverse high-performance submissions from academia and industry worldwide, empirically validating the feasibility and effectiveness of community-driven cybersecurity research.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy

Application Category

• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

The MIT/IEEE/Amazon GraphChallenge encourages community approaches to developing new solutions for analyzing graphs and sparse data derived from social media, sensor feeds, and scientific data to discover relationships between events as they unfold in the field. The anonymized network sensing Graph Challenge seeks to enable large, open, community-based approaches to protecting networks. Many large-scale networking problems can only be solved with community access to very broad data sets with the highest regard for privacy and strong community buy-in. Such approaches often require community-based data sharing. In the broader networking community (commercial, federal, and academia) anonymized source-to-destination traffic matrices with standard data sharing agreements have emerged as a data product that can meet many of these requirements. This challenge provides an opportunity to highlight novel approaches for optimizing the construction and analysis of anonymized traffic matrices using over 100 billion network packets derived from the largest Internet telescope in the world (CAIDA). This challenge specifies the anonymization, construction, and analysis of these traffic matrices. A GraphBLAS reference implementation is provided, but the use of GraphBLAS is not required in this Graph Challenge. As with prior Graph Challenges the goal is to provide a well-defined context for demonstrating innovation. Graph Challenge participants are free to select (with accompanying explanation) the Graph Challenge elements that are appropriate for highlighting their innovations.

Problem

• Develop solutions for analyzing anonymized network graphs
• Protect networks using community-based data sharing approaches
• Optimize construction and analysis of anonymized traffic matrices

Innovation

• Anonymized traffic matrices for privacy protection
• Community-based data sharing for large-scale networking
• GraphBLAS reference implementation for graph analysis