# DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation

Source: [DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation](<https://www.sota2.com/research/paper/68fa73d61e209131cea5e67d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-25T04:09:23.021Z

Authors: Yingying Fang, Shuang Wu, Zihao Jin, Caiwen Xu, Shiyi Wang, Simon Walsh, Guang Yang

Published: 2024-06-21T14:27:02.000Z

## Abstract

In the field of medical imaging, particularly in tasks related to early disease detection and prognosis, understanding the reasoning behind AI model predictions is imperative for assessing their reliability. Conventional explanation methods encounter challenges in identifying decisive features in medical image classifications, especially when discriminative features are subtle or not immediately evident. To address this limitation, we propose an agent model capable of generating counterfactual images that prompt different decisions when plugged into a black box model. By employing this agent model, we can uncover influential image patterns that impact the black model's final predictions. Through our methodology, we efficiently identify features that influence decisions of the deep black box. We validated our approach in the rigorous domain of medical prognosis tasks, showcasing its efficacy and potential to enhance the reliability of deep learning models in medical image classification compared to existing interpretation methods. The code will be publicly available at https://github.com/ayanglab/DiffExplainer.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.15182>)

[PDF](<https://arxiv.org/pdf/2406.15182.pdf>)

[Implementation](<https://github.com/ayanglab/DiffExplainer>)
