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 511–520 of 1808 papers

Title	Date	Tasks	Status	Hype
Imperceptible Adversarial Attack on Deep Neural Networks from Image Boundary	Aug 29, 2023	Adversarial Attack	—Unverified	0
A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation	Aug 29, 2023	Adversarial AttackMachine Translation	CodeCode Available	0
On-Manifold Projected Gradient Descent	Aug 23, 2023	Adversarial Attack	—Unverified	0
PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification	Aug 22, 2023	Adversarial AttackBackdoor Attack	CodeCode Available	1
Multi-Instance Adversarial Attack on GNN-Based Malicious Domain Detection	Aug 22, 2023	Adversarial Attack	CodeCode Available	0
Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs	Aug 21, 2023	Adversarial AttackLink Prediction	CodeCode Available	0
On the Adversarial Robustness of Multi-Modal Foundation Models	Aug 21, 2023	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Enhancing Adversarial Attacks: The Similar Target Method	Aug 21, 2023	Adversarial Attack	CodeCode Available	0
Hiding Backdoors within Event Sequence Data via Poisoning Attacks	Aug 20, 2023	Adversarial Attack	—Unverified	0
Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method	Aug 19, 2023	Adversarial AttackAttribute	—Unverified	0

Show:10 25 50

← PrevPage 52 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