# Explaining Deep Learning Models with Constrained Adversarial Examples

arXiv: https://arxiv.org/abs/1906.10671 · HTML: https://mlsanity.com/paper/1906.10671/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2019.

## Built on by (most cited first, 19 of 19)

- [Cycle-Consistent Counterfactuals by Latent Transformations](https://mlsanity.com/paper/2203.15064/) (2022)
- [A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data](https://mlsanity.com/paper/2107.04680/) (2021)
- [Model-Based Counterfactual Synthesizer for Interpretation](https://mlsanity.com/paper/2106.08971/) (2021)
- [Differentially Private Counterfactuals via Functional Mechanism](https://mlsanity.com/paper/2208.02878/) (2022)
- [Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation](https://mlsanity.com/paper/2101.06930/) (2021)
- [Achieving Diversity in Counterfactual Explanations: a Review and Discussion](https://mlsanity.com/paper/2305.05840/) (2023)
- [When and How to Fool Explainable Models (and Humans) with Adversarial Examples](https://mlsanity.com/paper/2107.01943/) (2021)
- [Causal Learning for Socially Responsible AI](https://mlsanity.com/paper/2104.12278/) (2021)
- [A multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers](https://mlsanity.com/paper/2403.13940/) (2024)
- [An exact counterfactual-example-based approach to tree-ensemble models interpretability](https://mlsanity.com/paper/2105.14820/) (2021)
- [Privacy Implications of Explainable AI in Data-Driven Systems](https://mlsanity.com/paper/2406.15789/) (2024)
- [Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space](https://mlsanity.com/paper/2207.07710/) (2022)
- [Calculating and Visualizing Counterfactual Feature Importance Values](https://mlsanity.com/paper/2306.06506/) (2023)
- [Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanations](https://mlsanity.com/paper/2601.20449/) (2026)
- [Causality-based Counterfactual Explanation for Classification Models](https://mlsanity.com/paper/2105.00703/) (2021)
- [Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual Explanations](https://mlsanity.com/paper/2404.03348/) (2024)
- [Guidelines For The Choice Of The Baseline in XAI Attribution Methods](https://mlsanity.com/paper/2503.19813/) (2025)
- [Model-Free Counterfactual Subset Selection at Scale](https://mlsanity.com/paper/2502.08326/) (2025)
- [CEL: Comprehensive Counterfactual Explanations Library and Benchmark](https://mlsanity.com/paper/2607.22045/) (2026)

## Abstract (arXiv)

Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of explaining why a particular classification was made explain how a different outcome can be achieved. This gives the recipients of the explanation a better way to understand the outcome, and provides an actionable suggestion. We show that the introduced method of Constrained Adversarial Examples (CADEX) can be used in real world applications, and yields explanations which incorporate business or domain constraints such as handling categorical attributes and range constraints.