Adversarial Attack

An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.

Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1601–1625 of 1808 papers

Title	Date	Tasks	Status	Hype
Investigating Decision Boundaries of Trained Neural Networks	Aug 7, 2019	Adversarial Attack	—Unverified	0
MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks	Aug 6, 2019	Adversarial AttackAdversarial Attack Detection	CodeCode Available	0
A principled approach for generating adversarial images under non-smooth dissimilarity metrics	Aug 5, 2019	Adversarial Attack	CodeCode Available	0
Adversarial Self-Defense for Cycle-Consistent GANs	Aug 5, 2019	Adversarial AttackImage-to-Image Translation	CodeCode Available	0
A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models	Aug 4, 2019	Adversarial AttackGraph Embedding	CodeCode Available	0
Exploring the Robustness of NMT Systems to Nonsensical Inputs	Aug 3, 2019	Adversarial AttackDecoder	—Unverified	0
Black-box Adversarial ML Attack on Modulation Classification	Aug 1, 2019	Adversarial AttackBIG-bench Machine Learning	—Unverified	0
Adversarial Attack on Sentiment Classification	Aug 1, 2019	Adversarial AttackClassification	—Unverified	0
Nonconvex Zeroth-Order Stochastic ADMM Methods with Lower Function Query Complexity	Jul 30, 2019	Adversarial Attack	—Unverified	0
On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method	Jul 26, 2019	Adversarial AttackBayesian Optimization	CodeCode Available	0
Natural Adversarial Examples	Jul 16, 2019	Adversarial AttackData Augmentation	CodeCode Available	1
Affine Disentangled GAN for Interpretable and Robust AV Perception	Jul 6, 2019	Adversarial AttackAutonomous Vehicles	—Unverified	0
Adversarial Attacks in Sound Event Classification	Jul 4, 2019	Adversarial AttackClassification	—Unverified	0
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack	Jul 3, 2019	Adversarial Attack	CodeCode Available	0
Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency	Jul 1, 2019	Adversarial AttackClassification	CodeCode Available	0
Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"	Jul 1, 2019	Adversarial AttackAdversarial Defense	—Unverified	0
The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks	Jun 17, 2019	Adversarial AttackAdversarial Robustness	—Unverified	0
A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks	Jun 13, 2019	Adversarial AttackDeep Learning	—Unverified	0
Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks	Jun 11, 2019	Adversarial Attack	CodeCode Available	0
Mimic and Fool: A Task Agnostic Adversarial Attack	Jun 11, 2019	Adversarial AttackImage Captioning	CodeCode Available	0
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers	Jun 9, 2019	Adversarial AttackAdversarial Defense	CodeCode Available	1
Adversarial Attack Generation Empowered by Min-Max Optimization	Jun 9, 2019	Adversarial AttackAdversarial Robustness	CodeCode Available	0
Robustness for Non-Parametric Classification: A Generic Attack and Defense	Jun 7, 2019	Adversarial AttackAdversarial Defense	CodeCode Available	0
Efficient Project Gradient Descent for Ensemble Adversarial Attack	Jun 7, 2019	Adversarial Attack	CodeCode Available	0
Query-efficient Meta Attack to Deep Neural Networks	Jun 6, 2019	Adversarial AttackMeta-Learning	CodeCode Available	0

Show:10 25 50

← PrevPage 65 of 73Next →

All datasets CIFAR-10 CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ResNet20	Test Accuracy	89.95	89.95(1)	Community Verified
2	Xu et al.	Attack: PGD20	78.68	—	Unverified
3	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	78.13	—	Unverified
4	TRADES-ANCRA/ResNet18	Attack: AutoAttack	59.7	—	Unverified
5	AdvTraining [madry2018]	Attack: PGD20	48.44	—	Unverified
6	TRADES [zhang2019b]	Attack: PGD20	45.9	—	Unverified
7	XU-Net	Robust Accuracy	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	51.28	—	Unverified
2	multi-resolution self-ensembles	Attack: AutoAttack	47.85	—	Unverified