English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The broad adoption of Machine Learning (ML) in security-critical fieldsdemands the explainability of the approach. However, the research onunderstanding ML models, such as Random Forest (RF), is still in its infantstage. In this work, we leverage formal methods and logical reasoning todevelop a novel model-specific method for explaining the prediction of RF. Ourapproach is centered around Minimal Unsatisfiable Cores (MUC) and provides acomprehensive solution for feature importance, covering local and globalaspects, and adversarial sample analysis. Experimental results on severaldatasets illustrate the high quality of our feature importance measurement. Wealso demonstrate that our adversarial analysis outperforms the state-of-the-artmethod. Moreover, our method can produce a user-centered report, which helpsprovide recommendations in real-life applications.

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