paper-with-me

Papers

Saliency Methods for Explaining Adversarial Attacks

2019-08-22 · Jindong Gu, Volker Tresp

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.

📄 PDF Abstract BibTeX arXiv:1908.08413

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

Model-based Saliency for the Detection of Adversarial Examples

2019-09-25 · Lisa Schut, Yarin Gal

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

2021-06-15 · Dipesh Tamboli

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 LearningPrediction

SAD: Saliency Adversarial Defense without Adversarial Training

2021-01-01 · Yao Zhu, Jiacheng Sun, Zewei Chen, Zhenguo Li

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 Defense

SAD: Saliency-based Defenses Against Adversarial Examples

2020-03-10 · Richard Tran, David Patrick, Michael Geyer, Amanda Fernandez

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 Recognition

Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks

2021-02-22 · Ginevra Carbone, Guido Sanguinetti, Luca Bortolussi

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