paper-with-me

홈 › Papers

Fooling Network Interpretation in Image Classification

2018-12-06 · ICCV 2019 10 · Akshayvarun Subramanya, Vipin Pillai, Hamed Pirsiavash

Deep neural networks have been shown to be fooled rather easily using adversarial attack algorithms. Practical methods such as adversarial patches have been shown to be extremely effective in causing misclassification. However, these patches are highlighted using standard network interpretation algorithms, thus revealing the identity of the adversary. We show that it is possible to create adversarial patches which not only fool the prediction, but also change what we interpret regarding the cause of the prediction. Moreover, we introduce our attack as a controlled setting to measure the accuracy of interpretation algorithms. We show this using extensive experiments for Grad-CAM interpretation that transfers to occluding patch interpretation as well. We believe our algorithms can facilitate developing more robust network interpretation tools that truly explain the network's underlying decision making process.

📄 PDF Abstract BibTeX arXiv:1812.02843

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackClassificationDecision MakingGeneral Classificationimage-classificationImage ClassificationNetwork Interpretation

Similar Papers 제목 키워드 기반

Fooling Neural Network Interpretations via Adversarial Model Manipulation

2019-02-06 · NeurIPS 2019 12 · Juyeon Heo, Sunghwan Joo, Taesup Moon

We ask whether the neural network interpretation methods can be fooled via adversarial model manipulation, which is defined as a model fine-tuning step that aims to radically alter the explanations without hurting the ac…

modelNetwork Interpretation

SPOOF: Simple Pixel Operations for Out-of-Distribution Fooling

2025-12-05 · Ankit Gupta, Christoph Adami, Emily Dolson arxiv

Deep neural networks (DNNs) excel across image recognition tasks, yet continue to exhibit overconfidence on inputs that bear no resemblance to natural images. Revisiting the "fooling images" work introduced by Nguyen et …

Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition

2021-08-27 · Tatpong Katanyukul, Pisit Nakjai

This study investigates an application of a new probabilistic interpretation of a softmax output to Open-Set Recognition (OSR). Softmax is a mechanism wildly used in classification and object recognition. However, a soft…

ObjectObject RecognitionOpen Set Learning

FooBaR: Fault Fooling Backdoor Attack on Neural Network Training

2021-09-23 · Jakub Breier, Xiaolu Hou, Martín Ochoa, Jesus Solano

Neural network implementations are known to be vulnerable to physical attack vectors such as fault injection attacks. As of now, these attacks were only utilized during the inference phase with the intention to cause a m…

Backdoor Attackimage-classificationImage Classification

Art of singular vectors and universal adversarial perturbations

2017-09-11 · CVPR 2018 6 · Valentin Khrulkov, Ivan Oseledets

Vulnerability of Deep Neural Networks (DNNs) to adversarial attacks has been attracting a lot of attention in recent studies. It has been shown that for many state of the art DNNs performing image classification there ex…

image-classificationImage Classification