Pinned Loading

1. SubgraphXAI SubgraphXAI Public

   Graph-level explainability for graph neural networks (GNNs), with a focus on extracting, analysing, and reusing explanation subgraphs as first-class artefacts.

   Python 1

2. Adversarial-Detection-Engineering-Framework Adversarial-Detection-Engineering-Framework Public

   A framework and taxonomy for identifying, classifying, and reasoning about detection logic bugs in SIEM, EDR, and XDR rules, with concrete examples and real-world bypasses.

   56 6

3. KEAAttack KEAAttack Public

   Known Explanation Adversarial Attacks. KEAAttack is a research framework for studying adversarial attacks on Graph Neural Networks (GNNs) that explicitly leverage known explanations.

   Python

4. Detection-Logic-Exposures Detection-Logic-Exposures Public

   A catalog of real-world detection rule bypasses arising from ADE Detection Logic Bugs.