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 771–780 of 1808 papers

Title	Date	Tasks	Status	Hype	Score
Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?	Oct 29, 2020	Adversarial AttackAdversarial Attack Detection	—Unverified	0	0
AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systems	Mar 2, 2023	Adversarial AttackAutonomous Vehicles	—Unverified	0	0
Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers	Nov 28, 2018	Action RecognitionAdversarial Attack	—Unverified	0	0
CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator	Dec 16, 2019	Adversarial Attack	—Unverified	0	0
AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification	Nov 29, 2022	Adversarial AttackClassification	—Unverified	0	0
CAAD 2018: Iterative Ensemble Adversarial Attack	Nov 7, 2018	Adversarial Attack	—Unverified	0	0
Adversarial Attacks for Multi-view Deep Models	Jun 19, 2020	Adversarial Attack	—Unverified	0	0
Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network	Nov 25, 2021	Adversarial AttackDeblurring	—Unverified	0	0
BufferSearch: Generating Black-Box Adversarial Texts With Lower Queries	Nov 16, 2021	Adversarial Attacktext-classification	—Unverified	0	0
Btech thesis report on adversarial attack detection and purification of adverserially attacked images	May 9, 2022	Adversarial AttackAdversarial Attack Detection	—Unverified	0	0

Show:10 25 50

← PrevPage 78 of 181Next →

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