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
Generating Adversarial Inputs Using A Black-box Differential Technique	Jul 10, 2020	Adversarial Attack	—Unverified	0
Generating Black-Box Adversarial Examples in Sparse Domain	Jan 22, 2021	Adversarial Attackobject-detection	—Unverified	0
Benchmarking Adversarial Robustness	Dec 26, 2019	Adversarial AttackAdversarial Robustness	—Unverified	0
Adversarial RAW: Image-Scaling Attack Against Imaging Pipeline	Jun 2, 2022	Adversarial Attack	—Unverified	0
Generating Out of Distribution Adversarial Attack using Latent Space Poisoning	Dec 9, 2020	Adversarial Attack	—Unverified	0
Generating Semantic Adversarial Examples via Feature Manipulation	Jan 6, 2020	Adversarial AttackDisentanglement	—Unverified	0
Defending Against Adversarial Examples by Regularized Deep Embedding	Sep 25, 2019	Adversarial AttackAdversarial Robustness	—Unverified	0
Defending against Adversarial Attack towards Deep Neural Networks via Collaborative Multi-task Training	Mar 14, 2018	Adversarial Attack	—Unverified	0
I2VGuard: Safeguarding Images against Misuse in Diffusion-based Image-to-Video Models	Jan 1, 2025	Adversarial AttackImage to Video Generation	—Unverified	0
Defending Against Adversarial Attack in ECG Classification with Adversarial Distillation Training	Mar 14, 2022	Adversarial AttackClassification	—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