paper-with-me

Papers

A New Kind of Adversarial Example

2022-08-04 · Ali Borji

Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and perceptible perturbation is added to an image such that a model maintains its original decision, whereas a human will most likely make a mistake if forced to decide (or opt not to decide at all). Existing targeted attacks can be reformulated to synthesize such adversarial examples. Our proposed attack, dubbed NKE, is similar in essence to the fooling images, but is more efficient since it uses gradient descent instead of evolutionary algorithms. It also offers a new and unified perspective into the problem of adversarial vulnerability. Experimental results over MNIST and CIFAR-10 datasets show that our attack is quite efficient in fooling deep neural networks. Code is available at https://github.com/aliborji/NKE.

📄 PDF Abstract BibTeX arXiv:2208.02430

Code (1)

aliborji/nke 공식 구현

Tasks

Evolutionary Algorithms

Methods 이 논문이 사용한 방법론

OPT OPT is a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters. The model uses an AdamW optimizer and weight decay of 0.1. It follows a linear…

Similar Papers 제목 키워드 기반

Transferable Adversarial Attacks for Image and Video Object Detection

2018-11-30 · Xingxing Wei, Siyuan Liang, Ning Chen, Xiaochun Cao

Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, whic…

Generative Adversarial NetworkObjectobject-detectionObject Detection+1

Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reduction

2017-05-23 · Bin Liang, Hongcheng Li, Miaoqiang Su, Xirong Li 외

Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powe…

Quantization

Perlin Noise Improve Adversarial Robustness

2021-12-26 · Chengjun Tang, Kun Zhang, Chunfang Xing, Yong Ding 외

Adversarial examples are some special input that can perturb the output of a deep neural network, in order to make produce intentional errors in the learning algorithms in the production environment. Most of the present …

Adversarial Robustness

CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

2019-01-28 · Alberto Marchisio, Giorgio Nanfa, Faiq Khalid, Muhammad Abdullah Hanif 외

Capsule Networks preserve the hierarchical spatial relationships between objects, and thereby bears a potential to surpass the performance of traditional Convolutional Neural Networks (CNNs) in performing tasks like imag…

image-classificationImage ClassificationTraffic Sign Recognition

Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding

2019-07-30 · Utku Ozbulak, Arnout Van Messem, Wesley De Neve

Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target clas…

All