Domain-Adapted Granger Causality for Real-Time Cross-Slice Attack Attribution in 6G Networks

2025-10-04

AI Summary

To address the core challenge of distinguishing genuine causal relationships from spurious correlations in cross-slice attack provenance under 6G shared infrastructure, this paper proposes a domain-adaptive Granger causality inference framework. The method integrates dynamic resource contention modeling with statistical domain adaptation to enable real-time, interpretable causal attribution of cross-slice anomaly propagation, accompanied by formal statistical guarantees. Unlike conventional causal analysis approaches, our work is the first to explicitly embed infrastructure-level resource contention into the causal model, significantly enhancing robustness in complex, tightly coupled slice environments. Evaluated on over one thousand empirical attack scenarios, the framework achieves an attribution accuracy of 89.2% and sub-100 ms response latency—representing a 10.1 percentage-point improvement over the state-of-the-art.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Cross-slice attack attribution in 6G networks faces the fundamental challenge of distinguishing genuine causal relationships from spurious correlations in shared infrastructure environments. We propose a theoretically-grounded domain-adapted Granger causality framework that integrates statistical causal inference with network-specific resource modeling for real-time attack attribution. Our approach addresses key limitations of existing methods by incorporating resource contention dynamics and providing formal statistical guarantees. Comprehensive evaluation on a production-grade 6G testbed with 1,100 empirically-validated attack scenarios demonstrates 89.2% attribution accuracy with sub-100ms response time, representing a statistically significant 10.1 percentage point improvement over state-of-the-art baselines. The framework provides interpretable causal explanations suitable for autonomous 6G security orchestration.

Problem

• Distinguishing real causal relationships from spurious correlations
• Enabling real-time cross-slice attack attribution in 6G networks
• Addressing resource contention dynamics in shared infrastructure environments

Innovation

• Domain-adapted Granger causality framework for real-time attribution
• Integrates causal inference with network-specific resource modeling
• Provides statistical guarantees and handles resource contention dynamics