# Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach

arXiv: https://arxiv.org/abs/2009.14260 · HTML: https://mlsanity.com/paper/2009.14260/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 5 of 5)

- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [A Survey on AI Assurance](https://mlsanity.com/paper/2111.07505/) (2021)
- [Defense Against Explanation Manipulation](https://mlsanity.com/paper/2111.04303/) (2021)
- [Distance-Aware eXplanation Based Learning](https://mlsanity.com/paper/2309.05548/) (2023)
- [Ovarian Cancer Data Analysis using Deep Learning: A Systematic Review from the Perspectives of Key Features of Data Analysis and AI Assurance](https://mlsanity.com/paper/2311.11932/) (2023)

## Abstract (arXiv)

Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the gradients flow. Even though CNNs can correctly classify images, the underlying saliency maps could be erroneous in many cases. This can result in skepticism as to the validity of the model or its interpretation. We propose a novel approach for training trustworthy CNNs by penalizing parameter choices that result in inaccurate saliency maps generated during training. We add a penalty term for inaccurate saliency maps produced when the predicted label is correct, a penalty term for accurate saliency maps produced when the predicted label is incorrect, and a regularization term penalizing overly confident saliency maps. Experiments show increased classification performance, user engagement, and trust.