# Detecting Adversarial Perturbations with Saliency

arXiv: https://arxiv.org/abs/1803.08773 · HTML: https://mlsanity.com/paper/1803.08773/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2018.

## Built on by (most cited first, 8 of 8)

- [LiBRe: A Practical Bayesian Approach to Adversarial Detection](https://mlsanity.com/paper/2103.14835/) (2021)
- [Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart](https://mlsanity.com/paper/2105.14785/) (2021)
- [When and How to Fool Explainable Models (and Humans) with Adversarial Examples](https://mlsanity.com/paper/2107.01943/) (2021)
- [Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces](https://mlsanity.com/paper/2212.00727/) (2022)
- [ExAD: An Ensemble Approach for Explanation-based Adversarial Detection](https://mlsanity.com/paper/2103.11526/) (2021)
- [AdvFAS: A robust face anti-spoofing framework against adversarial examples](https://mlsanity.com/paper/2308.02116/) (2023)
- [Segmentation Fault: A Cheap Defense Against Adversarial Machine Learning](https://mlsanity.com/paper/2108.13617/) (2021)
- [Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challenges](https://mlsanity.com/paper/2408.00193/) (2024)

## Abstract (arXiv)

In this paper we propose a novel method for detecting adversarial examples by training a binary classifier with both origin data and saliency data. In the case of image classification model, saliency simply explain how the model make decisions by identifying significant pixels for prediction. A model shows wrong classification output always learns wrong features and shows wrong saliency as well. Our approach shows good performance on detecting adversarial perturbations. We quantitatively evaluate generalization ability of the detector, showing that detectors trained with strong adversaries perform well on weak adversaries.