Improving LIME Robustness with Smarter Locality Sampling

06/22/2020
by   Sean Saito, et al.
0

Explainability algorithms such as LIME have enabled machine learning systems to adopt transparency and fairness, which are important qualities in commercial use cases. However, recent work has shown that LIME's naive sampling strategy can be exploited by an adversary to conceal biased, harmful behavior. We propose to make LIME more robust by training a generative adversarial network to sample more realistic synthetic data which the explainer uses to generate explanations. Our experiments demonstrate that our proposed method demonstrates an increase in accuracy across three real-world datasets in detecting biased, adversarial behavior compared to vanilla LIME. This is achieved while maintaining comparable explanation quality, with up to 99.94% in top-1 accuracy in some cases.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/07/2022

Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations

While machine learning models have achieved unprecedented success in rea...
research
10/16/2022

Comparing Synthetic Tabular Data Generation Between a Probabilistic Model and a Deep Learning Model for Education Use Cases

The ability to generate synthetic data has a variety of use cases across...
research
04/24/2023

A Study on Improving Realism of Synthetic Data for Machine Learning

Synthetic-to-real data translation using generative adversarial learning...
research
02/05/2021

Removing biased data to improve fairness and accuracy

Machine learning systems are often trained using data collected from his...
research
05/23/2019

Generative Adversarial Networks for Mitigating Biases in Machine Learning Systems

In this paper, we propose a new framework for mitigating biases in machi...
research
07/20/2020

Towards Ground Truth Explainability on Tabular Data

In data science, there is a long history of using synthetic data for met...
research
02/23/2022

Margin-distancing for safe model explanation

The growing use of machine learning models in consequential settings has...

Please sign up or login with your details

Forgot password? Click here to reset