# Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness

arXiv: https://arxiv.org/abs/1906.02896 · HTML: https://mlsanity.com/paper/1906.02896/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2019.

## Built on by (most cited first, 14 of 14)

- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Deepfake Detection: A Comprehensive Survey from the Reliability Perspective](https://mlsanity.com/paper/2211.10881/) (2022)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Diagrammatization and Abduction to Improve AI Interpretability With Domain-Aligned Explanations for Medical Diagnosis](https://mlsanity.com/paper/2302.01241/) (2023)
- [Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions](https://mlsanity.com/paper/2106.10947/) (2021)
- [Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience](https://mlsanity.com/paper/2306.06909/) (2023)
- [Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks](https://mlsanity.com/paper/2312.08651/) (2023)
- [Large-scale cervical precancerous screening via AI-assisted cytology whole slide image analysis](https://mlsanity.com/paper/2407.19512/) (2024)
- [Counterfactual Image Generation for adversarially robust and interpretable Classifiers](https://mlsanity.com/paper/2310.00761/) (2023)
- [Learning Fourier shapes to probe the geometric world of deep neural networks](https://mlsanity.com/paper/2511.04970/) (2025)
- [Evaluating Adversarial Robustness with Expected Viable Performance](https://mlsanity.com/paper/2309.09928/) (2023)
- [Combining AI Control Systems and Human Decision Support via Robustness and Criticality](https://mlsanity.com/paper/2407.03210/) (2024)
- [Criticality and Safety Margins for Reinforcement Learning](https://mlsanity.com/paper/2409.18289/) (2024)

## Abstract (arXiv)

For sensitive problems, such as medical imaging or fraud detection, Neural Network (NN) adoption has been slow due to concerns about their reliability, leading to a number of algorithms for explaining their decisions. NNs have also been found vulnerable to a class of imperceptible attacks, called adversarial examples, which arbitrarily alter the output of the network. Here we demonstrate both that these attacks can invalidate prior attempts to explain the decisions of NNs, and that with very robust networks, the attacks themselves may be leveraged as explanations with greater fidelity to the model. We show that the introduction of a novel regularization technique inspired by the Lipschitz constraint, alongside other proposed improvements, greatly improves an NN's resistance to adversarial examples. On the ImageNet classification task, we demonstrate a network with an Accuracy-Robustness Area (ARA) of 0.0053, an ARA 2.4x greater than the previous state of the art. Improving the mechanisms by which NN decisions are understood is an important direction for both establishing trust in sensitive domains and learning more about the stimuli to which NNs respond.