MUC-driven Feature Importance Measurement and Adversarial Analysis for Random Forest

TL;DR

This paper introduces a novel, formal-method-based approach for explaining Random Forest predictions, assessing feature importance, and analyzing adversarial samples, with superior performance demonstrated on multiple datasets.

Contribution

It presents a new model-specific explanation method for RF using MUCs, covering local/global importance and adversarial analysis, outperforming existing techniques.

Findings

High-quality feature importance measurement

Outperforms state-of-the-art adversarial analysis methods

Produces user-centered reports for practical applications

Abstract

The broad adoption of Machine Learning (ML) in security-critical fields demands the explainability of the approach. However, the research on understanding ML models, such as Random Forest (RF), is still in its infant stage. In this work, we leverage formal methods and logical reasoning to develop a novel model-specific method for explaining the prediction of RF. Our approach is centered around Minimal Unsatisfiable Cores (MUC) and provides a comprehensive solution for feature importance, covering local and global aspects, and adversarial sample analysis. Experimental results on several datasets illustrate the high quality of our feature importance measurement. We also demonstrate that our adversarial analysis outperforms the state-of-the-art method. Moreover, our method can produce a user-centered report, which helps provide recommendations in real-life applications.