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 781–790 of 1808 papers

Title	Date	Tasks	Status	Hype
Generative Adversarial Network-Driven Detection of Adversarial Tasks in Mobile Crowdsensing	Feb 16, 2022	Adversarial AttackAdversarial Attack Detection	—Unverified	0
GradMDM: Adversarial Attack on Dynamic Networks	Apr 1, 2023	Adversarial AttackDynamic neural networks	—Unverified	0
GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm	Jan 24, 2025	Adversarial AttackComputational Efficiency	—Unverified	0
Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detection	Jul 31, 2023	Adversarial AttackInformation Retrieval	—Unverified	0
Analyzing Robustness of the Deep Reinforcement Learning Algorithm in Ramp Metering Applications Considering False Data Injection Attack and Defense	Jan 28, 2023	Adversarial AttackDeep Reinforcement Learning	—Unverified	0
Defense-guided Transferable Adversarial Attacks	Oct 22, 2020	Adversarial Attack	—Unverified	0
Analytically Tractable Hidden-States Inference in Bayesian Neural Networks	Jul 8, 2021	Adversarial AttackBayesian Inference	—Unverified	0
Feature Importance Guided Attack: A Model Agnostic Adversarial Attack	Jun 28, 2021	Adversarial AttackFeature Importance	—Unverified	0
Adversarial Attack with Pattern Replacement	Nov 25, 2019	Adversarial Attack	—Unverified	0
Generating Semantically Valid Adversarial Questions for TableQA	May 26, 2020	Adversarial AttackQuestion Answering	—Unverified	0

Show:10 25 50

← PrevPage 79 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