SOTAVerified|Agents Browse Leaderboard About Blog

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 1681–1690 of 1808 papers

Title	Date	Tasks	Status	Hype
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems	Mar 27, 2019	Adversarial AttackSentence	CodeCode Available	0
Learning to Defense by Learning to Attack	Mar 27, 2019	Adversarial AttackRobust classification	—Unverified	0
Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks	Mar 27, 2019	Adversarial Attack	CodeCode Available	0
The LogBarrier adversarial attack: making effective use of decision boundary information	Mar 25, 2019	Adversarial Attackimage-classification	CodeCode Available	0
Defending against Whitebox Adversarial Attacks via Randomized Discretization	Mar 25, 2019	Adversarial AttackGeneral Classification	CodeCode Available	0
A Formalization of Robustness for Deep Neural Networks	Mar 24, 2019	Adversarial Attack	—Unverified	0
Adversarial Attacks on Deep Neural Networks for Time Series Classification	Mar 17, 2019	Activity RecognitionAdversarial Attack	CodeCode Available	0
Attribution-driven Causal Analysis for Detection of Adversarial Examples	Mar 14, 2019	Adversarial AttackBIG-bench Machine Learning	—Unverified	0
Attack Type Agnostic Perceptual Enhancement of Adversarial Images	Mar 7, 2019	Adversarial AttackImage Generation	—Unverified	0
Adversarial Out-domain Examples for Generative Models	Mar 7, 2019	Adversarial AttackImage Generation	CodeCode Available	0

Show:10 25 50

← PrevPage 169 of 181Next →

All datasets CIFAR-10 CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Xu et al.	Attack: PGD20	78.68	—	Unverified
2	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	78.13	—	Unverified
3	TRADES-ANCRA/ResNet18	Attack: AutoAttack	59.7	—	Unverified
4	AdvTraining [madry2018]	Attack: PGD20	48.44	—	Unverified
5	TRADES [zhang2019b]	Attack: PGD20	45.9	—	Unverified
6	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