Why Is SHAP Not a Reliable Standalone Explanation Framework for Malware Detection?
arXiv paper shows SHAP gives unreliable standalone explanations for malware detection, with attribution dilution and sign reversal in dependent PE feature spaces.
The paper argues SHAP's formal guarantees are insufficient for reliable malware interpretation because the explained feature-coalition game is fixed only by analyst choices, not by malware behavior in the data. In static Portable Executable feature spaces, dependent feature groups cause conditional SHAP to dilute credit by a factor of 1/m across redundant features, attribute importance to features the model never uses, and even reverse attribution signs; interventional SHAP queries off-manifold coalitions no real executable exhibits. Experiments on EMBER-2018, EMBER-2024, and BODMAS with fixed LightGBM and XGBoost detectors confirm these effects. The authors position SHAP as a limited diagnostic requiring explicit data-distribution statements and domain validation, not a standalone explanation framework.
- Conditional SHAP dilutes credit 1/m across redundant dependent features
- Interventional SHAP queries off-manifold coalitions no real executable exhibits
- Validated on EMBER-2018, EMBER-2024, BODMAS with LightGBM and XGBoost
- Authors recommend SHAP only as a diagnostic with domain validation
From the original article
1 min read at arxiv.orgMachine learning is widely used for malware detection, but its decisions must be explained. An analyst needs to know whether a model has learned genuine malicious behavior or only dataset-specific patterns \cite{gaur2021semantics}. SHapley Additive exPlanations (SHAP) is the standard tool for this, backed by formal properties such as local accuracy, missingness, and consistency.
By Seyedreza Mohseni · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.