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 1001–1010 of 1808 papers

Title	Date	Tasks	Status	Hype
Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders	Jul 19, 2022	Adversarial AttackAdversarial Defense	CodeCode Available	0
Multi-step domain adaptation by adversarial attack to H ΔH-divergence	Jul 18, 2022	Adversarial AttackDomain Adaptation	—Unverified	0
DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking	Jul 17, 2022	Adversarial AttackMiscellaneous	—Unverified	0
Adversarial Examples for Model-Based Control: A Sensitivity Analysis	Jul 14, 2022	Adversarial AttackSensitivity	—Unverified	0
How many perturbations break this model? Evaluating robustness beyond adversarial accuracy	Jul 8, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available	0
On the Relationship Between Adversarial Robustness and Decision Region in Deep Neural Network	Jul 7, 2022	Adversarial AttackAdversarial Robustness	—Unverified	0
Query-Efficient Adversarial Attack Based on Latin Hypercube Sampling	Jul 5, 2022	Adversarial Attack	CodeCode Available	0
Learning to Accelerate Approximate Methods for Solving Integer Programming via Early Fixing	Jul 5, 2022	Adversarial AttackImitation Learning	CodeCode Available	0
RAF: Recursive Adversarial Attacks on Face Recognition Using Extremely Limited Queries	Jul 4, 2022	Adversarial AttackFace Recognition	—Unverified	0
ZhichunRoad at SemEval-2022 Task 2: Adversarial Training and Contrastive Learning for Multiword Representations	Jul 1, 2022	Adversarial AttackContrastive Learning	—Unverified	0

Show:10 25 50

← PrevPage 101 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