SOTAVerified|Agents Browse Leaderboard About

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 1251–1260 of 1808 papers

Title	Date	Tasks	Status	Hype
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification	Dec 21, 2020	Adversarial AttackBackdoor Attack	CodeCode Available	1
Variational Quantum Cloning: Improving Practicality for Quantum Cryptanalysis	Dec 21, 2020	Adversarial AttackCryptanalysis	—Unverified	0
Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks	Dec 21, 2020	Adversarial AttackDimensionality Reduction	—Unverified	0
Blurring Fools the Network -- Adversarial Attacks by Feature Peak Suppression and Gaussian Blurring	Dec 21, 2020	Adversarial Attack	—Unverified	0
Efficient Training of Robust Decision Trees Against Adversarial Examples	Dec 18, 2020	Adversarial Attack	CodeCode Available	1
A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks	Dec 17, 2020	Adversarial AttackDecision Making	CodeCode Available	0
Exacerbating Algorithmic Bias through Fairness Attacks	Dec 16, 2020	Adversarial AttackBIG-bench Machine Learning	CodeCode Available	0
A Distributed Black-Box Adversarial Attack Based on Multi-Group Particle Swarm Optimization	Dec 14, 2020	Adversarial Attack	CodeCode Available	0
Disentangled Information Bottleneck	Dec 14, 2020	Adversarial AttackOut-of-Distribution Detection	CodeCode Available	1
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs	Dec 12, 2020	Adversarial AttackGraph Classification	—Unverified	0

Show:10 25 50

← PrevPage 126 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