# Robust Attribution Regularization

arXiv: https://arxiv.org/abs/1905.09957 · HTML: https://mlsanity.com/paper/1905.09957/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2019.

## Built on by (most cited first, 30 of 47)

- [When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?](https://mlsanity.com/paper/2111.01124/) (2021)
- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [Fast Axiomatic Attribution for Neural Networks](https://mlsanity.com/paper/2111.07668/) (2021)
- [TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization](https://mlsanity.com/paper/2303.05506/) (2023)
- [NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights](https://mlsanity.com/paper/2106.10185/) (2021)
- [Robust Explanation Constraints for Neural Networks](https://mlsanity.com/paper/2212.08507/) (2022)
- [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](https://mlsanity.com/paper/2211.05667/) (2022)
- [Robust Models Are More Interpretable Because Attributions Look Normal](https://mlsanity.com/paper/2103.11257/) (2021)
- [On the Lack of Robust Interpretability of Neural Text Classifiers](https://mlsanity.com/paper/2106.04631/) (2021)
- [Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanations](https://mlsanity.com/paper/2101.09498/) (2021)
- [Are Data-driven Explanations Robust against Out-of-distribution Data?](https://mlsanity.com/paper/2303.16390/) (2023)
- [DEAL: Disentangle and Localize Concept-level Explanations for VLMs](https://mlsanity.com/paper/2407.14412/) (2024)
- [Fooling Explanations in Text Classifiers](https://mlsanity.com/paper/2206.03178/) (2022)
- [Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation](https://mlsanity.com/paper/2203.12709/) (2022)
- [When and How to Fool Explainable Models (and Humans) with Adversarial Examples](https://mlsanity.com/paper/2107.01943/) (2021)
- [BadVFL: Backdoor Attacks in Vertical Federated Learning](https://mlsanity.com/paper/2304.08847/) (2023)
- [Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density](https://mlsanity.com/paper/2407.04370/) (2024)
- [It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness](https://mlsanity.com/paper/2303.09767/) (2023)
- [Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection](https://mlsanity.com/paper/2205.07279/) (2022)
- [On the Robustness of Explanations of Deep Neural Network Models: A Survey](https://mlsanity.com/paper/2211.04780/) (2022)
- [Towards More Robust Interpretation via Local Gradient Alignment](https://mlsanity.com/paper/2211.15900/) (2022)
- [AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments](https://mlsanity.com/paper/2310.06514/) (2023)
- [Rethinking Robustness of Model Attributions](https://mlsanity.com/paper/2312.10534/) (2023)
- [Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors](https://mlsanity.com/paper/2603.15656/) (2026)
- [More Than Words: Towards Better Quality Interpretations of Text Classifiers](https://mlsanity.com/paper/2112.12444/) (2021)
- [Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification System](https://mlsanity.com/paper/2209.04326/) (2022)
- [Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification](https://mlsanity.com/paper/2212.05327/) (2022)
- [A Practical Upper Bound for the Worst-Case Attribution Deviations](https://mlsanity.com/paper/2303.00340/) (2023)
- [Combining Machine Learning Defenses without Conflicts](https://mlsanity.com/paper/2411.09776/) (2024)

## Abstract (arXiv)

An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatically attributing a neural network's output change to its input change. We propose training objectives in classic robust optimization models to achieve robust IG attributions. Our objectives give principled generalizations of previous objectives designed for robust predictions, and they naturally degenerate to classic soft-margin training for one-layer neural networks. We also generalize previous theory and prove that the objectives for different robust optimization models are closely related. Experiments demonstrate the effectiveness of our method, and also point to intriguing problems which hint at the need for better optimization techniques or better neural network architectures for robust attribution training.