SOTAVerified|Agents Browse Leaderboard About Blog

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 1651–1660 of 1808 papers

Title	Date	Tasks	Status	Hype
Revisiting DeepFool: generalization and improvement	Mar 22, 2023	Adversarial AttackAdversarial Robustness	CodeCode Available	0
Adversarial Attack via Dual-Stage Network Erosion	Jan 1, 2022	Adversarial Attack	CodeCode Available	0
Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration	Mar 7, 2023	Adversarial Attack	CodeCode Available	0
Logits are predictive of network type	Nov 4, 2022	Adversarial AttackVocal Bursts Type Prediction	CodeCode Available	0
Look Closer to Your Enemy: Learning to Attack via Teacher-Student Mimicking	Jul 27, 2022	Adversarial AttackDomain Adaptation	CodeCode Available	0
LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate	May 22, 2024	Adversarial AttackAttribute	CodeCode Available	0
AdjointDEIS: Efficient Gradients for Diffusion Models	May 23, 2024	Adversarial Attack	CodeCode Available	0
LP-BFGS attack: An adversarial attack based on the Hessian with limited pixels	Oct 26, 2022	Adversarial Attack	CodeCode Available	0
RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World	Jul 14, 2023	Adversarial AttackObject	CodeCode Available	0
Adversarial Attack Generation Empowered by Min-Max Optimization	Jun 9, 2019	Adversarial AttackAdversarial Robustness	CodeCode Available	0

Show:10 25 50

← PrevPage 166 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