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 1121–1130 of 1808 papers

Title	Date	Tasks	Status	Hype
TASA: Twin Answer Sentences Attack for Adversarial Context Generation in Question Answering	Dec 17, 2021	Adversarial AttackQuestion Answering	—Unverified	0
Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering	Dec 17, 2021	Adversarial AttackMulti-hop Question Answering	—Unverified	0
Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network	Dec 17, 2021	3D Classification3D Semantic Segmentation	CodeCode Available	0
Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning	Dec 16, 2021	Adversarial AttackImage Compression	—Unverified	0
NOMARO: Defending against Adversarial Attacks by NOMA-Inspired Reconstruction Operation	Dec 14, 2021	Adversarial AttackAdversarial Defense	CodeCode Available	0
MedAttacker: Exploring Black-Box Adversarial Attacks on Risk Prediction Models in Healthcare	Dec 11, 2021	Adversarial AttackPosition	—Unverified	0
How Private Is Your RL Policy? An Inverse RL Based Analysis Framework	Dec 10, 2021	Adversarial AttackAutonomous Driving	CodeCode Available	0
Learning to Learn Transferable Attack	Dec 10, 2021	Adversarial AttackData Augmentation	CodeCode Available	0
Amicable Aid: Perturbing Images to Improve Classification Performance	Dec 9, 2021	Adversarial AttackClassification	—Unverified	0
SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization	Dec 8, 2021	Adversarial AttackAdversarial Robustness	—Unverified	0

Show:10 25 50

← PrevPage 113 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