Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection

TL;DR

This paper introduces a routing-aware explanation method for Mixture-of-Experts graph models in malware detection, enhancing interpretability and accuracy by leveraging diverse structural cues in control flow graphs.

Contribution

It proposes a novel MoE architecture with multi-statistic node encoding and explicit routing, improving transparency and performance in malware graph analysis.

Findings

Achieves strong detection accuracy on CFG dataset

Provides stable, faithful attributions under perturbations

Enhances interpretability of MoE decisions

Abstract

Mixture-of-Experts (MoE) offers flexible graph reasoning by combining multiple views of a graph through a learned router. We investigate routing-aware explanations for MoE graph models in malware detection using control flow graphs (CFGs). Our architecture builds diversity at two levels. At the node level, each layer computes multiple neighborhood statistics and fuses them with an MLP, guided by a degree reweighting factor rho and a pooling choice lambda in {mean, std, max}, producing distinct node representations that capture complementary structural cues in CFGs. At the readout level, six experts, each tied to a specific (rho, lambda) view, output graph-level logits that the router weights into a final prediction. Post-hoc explanations are generated with edge-level attributions per expert and aggregated using the router gates so the rationale reflects both what each expert highlights and how strongly it is selected. Evaluated against single-expert GNN baselines such as GCN, GIN, and GAT on the same CFG dataset, the proposed MoE achieves strong detection accuracy while yielding stable, faithful attributions under sparsity-based perturbations. The results indicate that making the router explicit and combining multi-statistic node encoding with expert-level diversity can improve the transparency of MoE decisions for malware analysis.