Topology aware anomaly detection improves some intrusion systems

TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings

Cryptography and SecurityArtificial Intelligence

Summary

Detecting computer attacks is hard when examples of attacks are rare or incomplete. The authors propose TRACE, a method that learns normal behavior from system activity represented as graphs without needing examples of attacks. TRACE uses graph structures and topology to spot unusual patterns likely caused by attacks. When tested on several datasets, TRACE did better than similar methods in some cases but not all, showing it can help in certain situations but is not always the best choice.

What this means in practice

  • For cybersecurity teams: Improve intrusion detection by spotting anomalies in network activity graphs without needing many labeled attack examples.
  • For industrial control operators: Monitor complex system interactions to find unusual behavior using topology-aware graph methods even when attack data is scarce.

Authors

Sydney Johns

Abstract

Intrusion detectors must recognize evolving malicious behavior even when confirmed attack labels are scarce or incomplete. We present TRACE, a topology-aware graph contrastive learning framework for label-efficient intrusion detection. TRACE learns from benign system-activity graphs by combining message-passing and topological representations, then assigns anomaly scores in the same projected embedding space optimized by the contrastive objective. This design captures both local interactions and graph-scale structural deviations without using attack labels during representation learning. A labeled validation set containing benign and malicious graphs is used only to calibrate the anomaly threshold. We evaluate TRACE on StreamSpot, GraSec-IoT, and Unicorn Wget against a supervised graph neural network and the benign-only GraphCL baseline. TRACE obtains F1 scores of 0.923, 0.790, and 0.583, respectively. Compared with GraphCL, this is higher on StreamSpot (0.450) and Unicorn Wget (0.203), but lower on GraSec-IoT (0.975). The supervised model leads on StreamSpot and GraSec-IoT, whereas TRACE has the highest F1 on Unicorn Wget. The mixed results show that topology-aware benign-only learning can improve detection in some graph settings but does not provide a uniform advantage.