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 691–700 of 1808 papers

Title	Date	Tasks	Status	Hype	Score
Fashion-Guided Adversarial Attack on Person Segmentation	Apr 17, 2021	Adversarial AttackHuman Instance Segmentation	CodeCode Available	0	5
Explainable and Safe Reinforcement Learning for Autonomous Air Mobility	Nov 24, 2022	Adversarial AttackDeep Reinforcement Learning	CodeCode Available	0	5
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection	Nov 8, 2023	Active LearningAdversarial Attack	CodeCode Available	0	5
Excess Capacity and Backdoor Poisoning	Sep 2, 2021	Adversarial AttackBackdoor Attack	CodeCode Available	0	5
Expanding Scope: Adapting English Adversarial Attacks to Chinese	Jun 8, 2023	Adversarial AttackAdversarial Robustness	CodeCode Available	0	5
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attack	Nov 22, 2018	Adversarial AttackAdversarial Defense	CodeCode Available	0	5
Explainable Graph Neural Networks Under Fire	Jun 10, 2024	Adversarial Attack	CodeCode Available	0	5
Feature Space Perturbations Yield More Transferable Adversarial Examples	Jun 1, 2019	Adversarial Attack	CodeCode Available	0	5
Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack	Jan 18, 2024	Adversarial AttackStyle Transfer	CodeCode Available	0	5
Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial Training	Mar 2, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	0	5

Show:10 25 50

← PrevPage 70 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