# Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach

arXiv: https://arxiv.org/abs/2405.06278 · HTML: https://mlsanity.com/paper/2405.06278/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 10 May 2024.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [Improving Deep Learning Interpretability by Saliency Guided Training](https://mlsanity.com/paper/2111.14338/) (2021)
- [ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints](https://mlsanity.com/paper/2201.01621/) (2022)
- [Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification System](https://mlsanity.com/paper/2209.04326/) (2022)

## Built on by (most cited first, 7 of 7)

- [Adversarial Examples Are Not Bugs, They Are Superposition](https://mlsanity.com/paper/2508.17456/) (2025)
- [Navigating Threats: A Survey of Physical Adversarial Attacks on LiDAR Perception Systems in Autonomous Vehicles](https://mlsanity.com/paper/2409.20426/) (2024)
- [H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition](https://mlsanity.com/paper/2510.20627/) (2025)
- [A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challenges](https://mlsanity.com/paper/2503.00384/) (2025)
- [Explanation-Guided Adversarial Training for Robust and Interpretable Models](https://mlsanity.com/paper/2603.01938/) (2026)
- [Are Inherently Interpretable Models More Robust? A Study In Music Emotion Recognition](https://mlsanity.com/paper/2508.03780/) (2025)
- [From Attribution to Action: Jointly ALIGNing Predictions and Explanations](https://mlsanity.com/paper/2511.06944/) (2025)

## Abstract (arXiv)

Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is vital for fostering trust and comprehension in these models. This study investigates the impact of Saliency-guided Training (SGT) on model robustness, a technique aimed at improving the clarity of saliency maps to deepen understanding of the model's decision-making process. Experiments were conducted on standard benchmark datasets using various deep learning architectures trained with and without SGT. Findings demonstrate that SGT enhances both model robustness and interpretability. Additionally, we propose a novel approach combining SGT with standard adversarial training to achieve even greater robustness while preserving saliency map quality. Our strategy is grounded in the assumption that preserving salient features crucial for correctly classifying adversarial examples enhances model robustness, while masking non-relevant features improves interpretability. Our technique yields significant gains, achieving a 35% and 20% improvement in robustness against PGD attack with noise magnitudes of 0.2 and 0.02 for the MNIST and CIFAR-10 datasets, respectively, while producing high-quality saliency maps.