# Detecting Adversarial Perturbations with Saliency

Source: [Detecting Adversarial Perturbations with Saliency](<https://www.sota2.com/research/paper/68fa64271e209131cea02f30>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:57:11.341Z

Authors: Chiliang Zhang, Zhimou Yang, Zuochang Ye

Published: 2018-03-23T12:52:28.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1803.08773>)

[PDF](<https://arxiv.org/pdf/1803.08773.pdf>)