Saliency Methods for Explaining Adversarial Attacks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Model-based Saliency for the Detection of Adversarial Examples
Adversarial perturbations cause a shift in the salient features of an image, which may result in a misclassification. We demonstrate that gradient-based saliency approaches are unable to capture this shift, and develop a…
Explaining decision of model from its prediction
This document summarizes different visual explanations methods such as CAM, Grad-CAM, Localization using Multiple Instance Learning - Saliency-based methods, Saliency-driven Class-Impressions, Muting pixels in input imag…
modelMultiple Instance LearningPredictionSAD: Saliency Adversarial Defense without Adversarial Training
Adversarial training is one of the most effective methods for defending adversarial attacks, but it is computationally costly. In this paper, we propose Saliency Adversarial Defense (SAD), an efficient defense algorithm …
Adversarial DefenseSAD: Saliency-based Defenses Against Adversarial Examples
With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of…
Adversarial AttackMusic Genre RecognitionResilience of Bayesian Layer-Wise Explanations under Adversarial Attacks
We consider the problem of the stability of saliency-based explanations of Neural Network predictions under adversarial attacks in a classification task. Saliency interpretations of deterministic Neural Networks are rema…
General Classification