These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
Given an input data sample, LEMNA generates a small set of interpretable features to explain how the input sample is classified. The core idea is to approximate a local area of the complex deep learning decision boundary using a simple interpretable model. The local interpretable model is specially designed to (1) handle feature dependency to better work with security applications (e.g., binary code analysis); and (2) handle nonlinear local boundaries to boost explanation fidelity.
LEMNA connects to Explainability by providing understandable, feature-based explanations for individual AI decisions, helping users and stakeholders comprehend how outputs are generated. It also supports Transparency by disclosing the reasoning process behind AI predictions, thus increasing openness and trust in the system's operation.
About the metric
You can click on the links to see the associated metrics
Objective(s):
Purpose(s):
Lifecycle stage(s):
Target users:
Risk management stage(s):
Github stars:
- 23
Github forks:
- 8
