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 1651–1675 of 1808 papers

Title	Date	Tasks	Status	Hype
Mitigating Deep Learning Vulnerabilities from Adversarial Examples Attack in the Cybersecurity Domain	May 9, 2019	Adversarial AttackDeep Reinforcement Learning	—Unverified	0
CharBot: A Simple and Effective Method for Evading DGA Classifiers	May 3, 2019	Adversarial Attack	—Unverified	0
Weight Map Layer for Noise and Adversarial Attack Robustness	May 2, 2019	Adversarial Attack	—Unverified	0
POBA-GA: Perturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithm	May 1, 2019	Adversarial AttackDiversity	—Unverified	0
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks	May 1, 2019	Adversarial Attack	CodeCode Available	0
CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild	May 1, 2019	Adversarial AttackObject	CodeCode Available	0
NATTACK: A STRONG AND UNIVERSAL GAUSSIAN BLACK-BOX ADVERSARIAL ATTACK	May 1, 2019	Adversarial Attack	—Unverified	0
Second-Order Adversarial Attack and Certifiable Robustness	May 1, 2019	Adversarial Attack	—Unverified	0
Adversarial Training for Free!	Apr 29, 2019	Adversarial AttackAdversarial Defense	CodeCode Available	1
Minimizing Perceived Image Quality Loss Through Adversarial Attack Scoping	Apr 23, 2019	Adversarial AttackAutonomous Vehicles	—Unverified	0
blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness	Apr 22, 2019	Adversarial Attack	—Unverified	0
Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks	Apr 18, 2019	Adversarial AttackAdversarial Attack Detection	CodeCode Available	0
Defensive Quantization: When Efficiency Meets Robustness	Apr 17, 2019	Adversarial AttackCPU	—Unverified	0
AT-GAN: An Adversarial Generator Model for Non-constrained Adversarial Examples	Apr 16, 2019	Adversarial Attack	—Unverified	0
Cycle-Consistent Adversarial GAN: the integration of adversarial attack and defense	Apr 12, 2019	Adversarial Attackimage-classification	—Unverified	0
Black-Box Decision based Adversarial Attack with Symmetric α-stable Distribution	Apr 11, 2019	Adversarial Attack	—Unverified	0
Towards Analyzing Semantic Robustness of Deep Neural Networks	Apr 9, 2019	Adversarial AttackAutonomous Driving	CodeCode Available	0
HopSkipJumpAttack: A Query-Efficient Decision-Based Attack	Apr 3, 2019	Adversarial Attack	CodeCode Available	0
Curls & Whey: Boosting Black-Box Adversarial Attacks	Apr 2, 2019	Adversarial AttackDiversity	CodeCode Available	0
Adversarial Attacks against Deep Saliency Models	Apr 2, 2019	Adversarial Attackobject-detection	—Unverified	0
Learning to Defense by Learning to Attack	Mar 27, 2019	Adversarial AttackRobust classification	—Unverified	0
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems	Mar 27, 2019	Adversarial AttackSentence	CodeCode Available	0
Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks	Mar 27, 2019	Adversarial Attack	CodeCode Available	0
Defending against Whitebox Adversarial Attacks via Randomized Discretization	Mar 25, 2019	Adversarial AttackGeneral Classification	CodeCode Available	0
The LogBarrier adversarial attack: making effective use of decision boundary information	Mar 25, 2019	Adversarial Attackimage-classification	CodeCode Available	0

Show:10 25 50

← PrevPage 67 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