paper-with-me

홈 › Papers

Recovering Localized Adversarial Attacks

2019-10-21 · Jan Philip Göpfert, Heiko Wersing, Barbara Hammer

Deep convolutional neural networks have achieved great successes over recent years, particularly in the domain of computer vision. They are fast, convenient, and -- thanks to mature frameworks -- relatively easy to implement and deploy. However, their reasoning is hidden inside a black box, in spite of a number of proposed approaches that try to provide human-understandable explanations for the predictions of neural networks. It is still a matter of debate which of these explainers are best suited for which situations, and how to quantitatively evaluate and compare them. In this contribution, we focus on the capabilities of explainers for convolutional deep neural networks in an extreme situation: a setting in which humans and networks fundamentally disagree. Deep neural networks are susceptible to adversarial attacks that deliberately modify input samples to mislead a neural network's classification, without affecting how a human observer interprets the input. Our goal with this contribution is to evaluate explainers by investigating whether they can identify adversarially attacked regions of an image. In particular, we quantitatively and qualitatively investigate the capability of three popular explainers of classifications -- classic salience, guided backpropagation, and LIME -- with respect to their ability to identify regions of attack as the explanatory regions for the (incorrect) prediction in representative examples from image classification. We find that LIME outperforms the other explainers.

📄 PDF Abstract BibTeX arXiv:1910.09239

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

Similar Papers 제목 키워드 기반

Localizing Adversarial Attacks To Produces More Imperceptible Noise

2025-09-23 · Pavan Reddy, Aditya Sanjay Gujral arxiv

Adversarial attacks in machine learning traditionally focus on global perturbations to input data, yet the potential of localized adversarial noise remains underexplored. This study systematically evaluates localized adv…

Computational Efficiency

Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks

2021-08-11 · Zitao Chen, Pritam Dash, Karthik Pattabiraman

Adversarial patch attacks create adversarial examples by injecting arbitrary distortions within a bounded region of the input to fool deep neural networks (DNNs). These attacks are robust (i.e., physically-realizable) an…

Image ClassificationImage InpaintingPrediction

DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination

2024-10-31 · Jia Fu, Xiao Zhang, Sepideh Pashami, Fatemeh Rahimian 외

In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Altho…

Adversarial RobustnessBinarizationDenoisingImage Generation+2

Local Gradients Smoothing: Defense against localized adversarial attacks

2018-07-03 · Muzammal Naseer, Salman H. Khan, Fatih Porikli

Deep neural networks (DNNs) have shown vulnerability to adversarial attacks, i.e., carefully perturbed inputs designed to mislead the network at inference time. Recently introduced localized attacks, Localized and Visibl…

Adversarial Attack

Localized Uncertainty Attacks

2021-06-17 · Ousmane Amadou Dia, Theofanis Karaletsos, Caner Hazirbas, Cristian Canton Ferrer 외

The susceptibility of deep learning models to adversarial perturbations has stirred renewed attention in adversarial examples resulting in a number of attacks. However, most of these attacks fail to encompass a large spe…