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 111–120 of 1808 papers

Title	Date	Tasks	Status	Hype
SAGA: Spectral Adversarial Geometric Attack on 3D Meshes	Nov 24, 2022	Adversarial Attack	CodeCode Available	1
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack	Nov 21, 2022	Activity RecognitionAdversarial Attack	CodeCode Available	1
T-SEA: Transfer-based Self-Ensemble Attack on Object Detection	Nov 16, 2022	Adversarial AttackModel Optimization	CodeCode Available	1
MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack	Nov 15, 2022	Adversarial Attack	CodeCode Available	1
Preserving Semantics in Textual Adversarial Attacks	Nov 8, 2022	Adversarial AttackSentence	CodeCode Available	1
Are AlphaZero-like Agents Robust to Adversarial Perturbations?	Nov 7, 2022	Adversarial AttackBoard Games	CodeCode Available	1
Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain	Nov 1, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Universal Perturbation Attack on Differentiable No-Reference Image- and Video-Quality Metrics	Nov 1, 2022	Adversarial AttackNo-Reference Image Quality Assessment	CodeCode Available	1
Rethinking Image Restoration for Object Detection	Nov 1, 2022	Adversarial AttackDomain Adaptation	CodeCode Available	1
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution	Oct 31, 2022	Adversarial AttackSentence	CodeCode Available	1

Show:10 25 50

← PrevPage 12 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