# Saliency Methods for Explaining Adversarial Attacks

arXiv: https://arxiv.org/abs/1908.08413 · HTML: https://mlsanity.com/paper/1908.08413/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2019.

## Built on by (most cited first, 16 of 16)

- [Are Vision Transformers Robust to Patch Perturbations?](https://mlsanity.com/paper/2111.10659/) (2021)
- [Attacking Adversarial Attacks as A Defense](https://mlsanity.com/paper/2106.04938/) (2021)
- [Explaining Chest X-ray Pathologies in Natural Language](https://mlsanity.com/paper/2207.04343/) (2022)
- [Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image](https://mlsanity.com/paper/2402.14899/) (2024)
- [Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis](https://mlsanity.com/paper/2102.12196/) (2021)
- [Graph Neural Network Causal Explanation via Neural Causal Models](https://mlsanity.com/paper/2407.09378/) (2024)
- [Visualizing Automatic Speech Recognition -- Means for a Better Understanding?](https://mlsanity.com/paper/2202.00673/) (2022)
- [Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense](https://mlsanity.com/paper/2304.06919/) (2023)
- [Saliency Diversified Deep Ensemble for Robustness to Adversaries](https://mlsanity.com/paper/2112.03615/) (2021)
- [Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities](https://mlsanity.com/paper/2308.08407/) (2023)
- [Understanding Robustness in Teacher-Student Setting: A New Perspective](https://mlsanity.com/paper/2102.13170/) (2021)
- [IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation](https://mlsanity.com/paper/2509.16678/) (2025)
- [Out-of-the-box: Black-box Causal Attacks on Object Detectors](https://mlsanity.com/paper/2512.03730/) (2025)
- [Explainability and Robustness of Deep Visual Classification Models](https://mlsanity.com/paper/2301.01343/) (2023)
- [A Lightweight Generative Model for Interpretable Subject-level Prediction](https://mlsanity.com/paper/2306.11107/) (2023)
- [Explaining Chest X-ray Pathology Models using Textual Concepts](https://mlsanity.com/paper/2407.00557/) (2024)

## Abstract (arXiv)

The classification decisions of neural networks can be misled by small imperceptible perturbations. This work aims to explain the misled classifications using saliency methods. The idea behind saliency methods is to explain the classification decisions of neural networks by creating so-called saliency maps. Unfortunately, a number of recent publications have shown that many of the proposed saliency methods do not provide insightful explanations. A prominent example is Guided Backpropagation (GuidedBP), which simply performs (partial) image recovery. However, our numerical analysis shows the saliency maps created by GuidedBP do indeed contain class-discriminative information. We propose a simple and efficient way to enhance the saliency maps. The proposed enhanced GuidedBP shows the state-of-the-art performance to explain adversary classifications.