# Improving LIME Robustness with Smarter Locality Sampling

arXiv: https://arxiv.org/abs/2006.12302 · HTML: https://mlsanity.com/paper/2006.12302/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [On Locality of Local Explanation Models](https://mlsanity.com/paper/2106.14648/) (2021)
- [Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainability](https://mlsanity.com/paper/2108.06907/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Manifold Restricted Interventional Shapley Values](https://mlsanity.com/paper/2301.04041/) (2023)
- [Better sampling in explanation methods can prevent dieselgate-like deception](https://mlsanity.com/paper/2101.11702/) (2021)
- [Don't Lie to Me: Avoiding Malicious Explanations with STEALTH](https://mlsanity.com/paper/2301.10407/) (2023)
- [EMaP: Explainable AI with Manifold-based Perturbations](https://mlsanity.com/paper/2209.08453/) (2022)
- [CLIMAX: An exploration of Classifier-Based Contrastive Explanations](https://mlsanity.com/paper/2307.00680/) (2023)
- [Coherent Local Explanations for Mathematical Optimization](https://mlsanity.com/paper/2502.04840/) (2025)
- [Causality-Aware Local Interpretable Model-Agnostic Explanations](https://mlsanity.com/paper/2212.05256/) (2022)
- [MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision -- A Medical Image Case Study](https://mlsanity.com/paper/2503.20758/) (2025)

## Abstract (arXiv)

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.