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 841–850 of 1808 papers

Title	Date	Tasks	Status	Hype
On the Perils of Cascading Robust Classifiers	Jun 1, 2022	Adversarial Attack	CodeCode Available	0
On the reversibility of adversarial attacks	Jun 1, 2022	Adversarial Attack	—Unverified	0
NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural Networks	Jun 1, 2022	Adversarial AttackGPU	CodeCode Available	1
Semantic Autoencoder and Its Potential Usage for Adversarial Attack	May 31, 2022	Adversarial Attack	—Unverified	0
Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models	May 30, 2022	Adversarial AttackAdversarial Robustness	—Unverified	0
Mixture GAN For Modulation Classification Resiliency Against Adversarial Attacks	May 29, 2022	Adversarial AttackClassification	—Unverified	0
On the Robustness of Safe Reinforcement Learning under Observational Perturbations	May 29, 2022	Adversarial Attackreinforcement-learning	CodeCode Available	1
Superclass Adversarial Attack	May 29, 2022	Adversarial AttackMulti-Label Classification	—Unverified	0
Unfooling Perturbation-Based Post Hoc Explainers	May 29, 2022	Adversarial AttackAnomaly Detection	CodeCode Available	0
Physical-World Optical Adversarial Attacks on 3D Face Recognition	May 26, 2022	Adversarial AttackFace Recognition	—Unverified	0

Show:10 25 50

← PrevPage 85 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