Bridging Interpretability and Robustness Using LIME-Guided Model Refinement

2024-12-25 · Navid Nayyem, Abdullah Rakin, Longwei Wang

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities, including susceptibility to adversarial attacks, over-reliance on spurious correlations, and a lack of transparency in their decision-making processes. To address these limitations, we propose a novel framework that leverages Local Interpretable Model-Agnostic Explanations (LIME) to systematically enhance model robustness. By identifying and mitigating the influence of irrelevant or misleading features, our approach iteratively refines the model, penalizing reliance on these features during training. Empirical evaluations on multiple benchmark datasets demonstrate that LIME-guided refinement not only improves interpretability but also significantly enhances resistance to adversarial perturbations and generalization to out-of-distribution data.

📄 PDF Abstract BibTeX arXiv:2412.18952

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDeep Learning

Explainability-Guided Defense: Attribution-Aware Model Refinement Against Adversarial Data Attacks

2026-01-02 · Longwei Wang, Mohammad Navid Nayyem, Abdullah Al Rakin, KC Santosh 외 arxiv

The growing reliance on deep learning models in safety-critical domains such as healthcare and autonomous navigation underscores the need for defenses that are both robust to adversarial perturbations and transparent in …

Adversarial Robustness

BOLIMES: Boruta and LIME optiMized fEature Selection for Gene Expression Classification

2025-02-18 · Bich-Chung Phan, Thanh Ma, Huu-Hoa Nguyen, and Thanh-Nghi Do

Gene expression classification is a pivotal yet challenging task in bioinformatics, primarily due to the high dimensionality of genomic data and the risk of overfitting. To bridge this gap, we propose BOLIMES, a novel fe…

Classification Dimensionality Reduction feature selection

Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning

2026-04-02 · Jiayi Chen, Shuai Wang, Guangxu Zhu, Chengzhong Xu arxiv

Large foundation models enable powerful reasoning for autonomous systems, but mapping semantic intent to reliable real-time control remains challenging. Existing approaches either (i) let Large Language Models (LLMs) gen…

A Novel XAI-Enhanced Quantum Adversarial Networks for Velocity Dispersion Modeling in MaNGA Galaxies

2025-10-28 · Sathwik Narkedimilli, N V Saran Kumar, Aswath Babu H, Manjunath K Vanahalli 외 arxiv

Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability. To address this, we propose a novel quantum adversarial framework that integrates a hybri…

Quantum Machine Learning

TRACE: Training-time Report-guided and Clinically Ordered Concept Editing

2026-08-21 · Wentao Yue, Tianyou Lai, Jiayu Luo, Qingyu Mao 외 arxiv

Breast ultrasound diagnosis relies on clinically meaningful semantic concepts, yet most deep learning methods adopt end-to-end image-to-label paradigms that lack interpretability and robustness. While concept-based appro…