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 481–490 of 1808 papers

Title	Date	Tasks	Status	Hype
Black-box Targeted Adversarial Attack on Segment Anything (SAM)	Oct 16, 2023	Adversarial Attack	—Unverified	0
Evading Detection Actively: Toward Anti-Forensics against Forgery Localization	Oct 16, 2023	Adversarial AttackSelf-Supervised Learning	—Unverified	0
A Non-monotonic Smooth Activation Function	Oct 16, 2023	Adversarial AttackAdversarial Robustness	—Unverified	0
Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models	Oct 11, 2023	Adversarial AttackDenoising	CodeCode Available	0
Adversarial optimization leads to over-optimistic security-constrained dispatch, but sampling can help	Oct 10, 2023	Adversarial AttackDiversity	—Unverified	0
Targeted Attack Improves Protection against Unauthorized Diffusion Customization	Oct 7, 2023	Adversarial AttackImage Generation	CodeCode Available	1
Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System	Oct 5, 2023	Adversarial AttackData Augmentation	—Unverified	0
Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria	Oct 5, 2023	Adversarial AttackAdversarial Defense	CodeCode Available	0
Optimizing Key-Selection for Face-based One-Time Biometrics via Morphing	Oct 4, 2023	Adversarial AttackBlocking	—Unverified	0
Adversarial Client Detection via Non-parametric Subspace Monitoring in the Internet of Federated Things	Oct 2, 2023	Adversarial AttackFederated Learning	—Unverified	0

Show:10 25 50

← PrevPage 49 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