paper-with-me

Papers

Explaining and Harnessing Adversarial Examples

2014-12-20 · Ian J. Goodfellow, Jonathon Shlens, Christian Szegedy

Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence. Early attempts at explaining this phenomenon focused on nonlinearity and overfitting. We argue instead that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature. This explanation is supported by new quantitative results while giving the first explanation of the most intriguing fact about them: their generalization across architectures and training sets. Moreover, this view yields a simple and fast method of generating adversarial examples. Using this approach to provide examples for adversarial training, we reduce the test set error of a maxout network on the MNIST dataset.

📄 PDF Abstract BibTeX arXiv:1412.6572

Code (59)

1Konny/FGSM pytorch
Anaststam/Adversarial-Attacks pytorch
AngusG/cleverhans-attacking-bnns tf
BendeguzToth/Fun-with-ConvNets
HowToMakeABomb101/Hot2MakeAB0mbSite tf
Jeffkang-94/pytorch-adversarial-attack pytorch
Jupetus/ExplainableAI pytorch
KaidongLi/pytorch-LatticePointClassifier pytorch
KeAWang/BayesianGAN4AdversarialAttacks tf
LamaLenny/Adversarial-Attack
LawrenceMMStewart/Adversarial_Attack pytorch
Mohammad-Rahmdel/FGSM-Tensorflow2-Caltech101 tf
OwenSec/DeepDetector tf
SifatMd/Research-Papers
Trustworthy-AI-Group/TransferAttack pytorch
Waleed-Mujahid/Fast-Gradient-Sign-method
albertmillan/adversarial-training-pytorch pytorch
amerch/CIFAR100-Training pytorch
anirudh9784/Adversarial-Attacks-and-Defences pytorch
anirudh9784/Adversarial-Defense tf
anirudh9784/Major_Project tf
arobey1/advbench pytorch
as791/Adversarial-Example-Attack-and-Defense torch
axelbrando/Mixture-Density-Networks-for-distribution-and-uncertainty-estimation tf
bingcheng45/hnr-extension tf
cfinlay/tulip pytorch
ckerce/pops_ml pytorch
cleverhans-lab/cleverhans tf
coallaoh/whitenblackbox pytorch
drewbarot/Un-CNN tf
dunky11/adversarial-frontier-stitching tf
eiriniOG/seedtag-codetest tf
elijahcn/TextCNN-AdversarialTraining pytorch
elites2k19/prism-attack tf
eth-sri/diffai pytorch
facebookresearch/adversarial_image_defenses pytorch
formal-verification-research/NJSMA tf
formal-verification-research/verapak tf
gauthiercler/adversarial-mnist pytorch
henry8527/GCE pytorch
iirishikaii/cleverhans tf
inhopark94/ihpark pytorch
jaxball/advis.js tf
jaypmorgan/Adversarial.jl pytorch
jrguo/FastGradientSignMNIST tf
katiashh/ioi-attack pytorch
littleredhat1997/captcha-adversarial-attack
locuslab/convex_adversarial pytorch
mkazmier/pytorch-fgsm-simple pytorch
openai/cleverhans tf
pgasawa/AdversarialAttacksOnFacialRecognition tf
sdemyanov/ConvNet tf
shijiel2/cleverhans tf
soumyac1999/FGSM-Keras tf
tensorflow/cleverhans tf
tensorflow/neural-structured-learning tf
winycg/HCGNet pytorch
xiuyu0000/papers_with_examples/tree/main/fgsm mindspore
yaq007/cleverhans tf

Tasks

Image Classification

Similar Papers 제목 키워드 기반

Harnessing adversarial examples with a surprisingly simple defense

2020-04-26 · Ali Borji

I introduce a very simple method to defend against adversarial examples. The basic idea is to raise the slope of the ReLU function at the test time. Experiments over MNIST and CIFAR-10 datasets demonstrate the effectiven…

Explaining Deep Learning Models with Constrained Adversarial Examples

2019-06-25 · Jonathan Moore, Nils Hammerla, Chris Watkins

Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative…

ClassificationcounterfactualDeep LearningGeneral Classification

Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks

2021-07-22 · Ramin Barati, Reza Safabakhsh, Mohammad Rahmati

In this paper, we study the adversarial examples existence and adversarial training from the standpoint of convergence and provide evidence that pointwise convergence in ANNs can explain these observations. The main cont…

Learning Theory

AdvGAN++ : Harnessing latent layers for adversary generation

2019-08-02 · Puneet Mangla, Surgan Jandial, Sakshi Varshney, Vineeth N. Balasubramanian

Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance. Recently proposed AdvGAN, a GAN based approach, takes input im…

Verifying the Causes of Adversarial Examples

2020-10-19 · Honglin Li, Yifei Fan, Frieder Ganz, Anthony Yezzi 외

The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence. Limited by the extrem…

Density Estimation