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 461–470 of 1808 papers

Title	Date	Tasks	Status	Hype
Robust Text Classification: Analyzing Prototype-Based Networks	Nov 11, 2023	Adversarial AttackClassification	CodeCode Available	0
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness	Nov 10, 2023	Adversarial AttackDiversity	CodeCode Available	0
Resilient and constrained consensus against adversarial attacks: A distributed MPC framework	Nov 10, 2023	Adversarial AttackAdversarial Attack Detection	—Unverified	0
Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous	Nov 10, 2023	Adversarial AttackAdversarial Attack Detection	—Unverified	0
ABIGX: A Unified Framework for eXplainable Fault Detection and Classification	Nov 9, 2023	Adversarial AttackClassification	—Unverified	0
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection	Nov 8, 2023	Active LearningAdversarial Attack	CodeCode Available	0
Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems	Nov 1, 2023	Adversarial Attack	—Unverified	0
Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning	Oct 31, 2023	Adversarial Attackreinforcement-learning	CodeCode Available	0
LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations	Oct 31, 2023	Adversarial Attack	—Unverified	0
Differentially Private Reward Estimation with Preference Feedback	Oct 30, 2023	Adversarial Attack	—Unverified	0

Show:10 25 50

← PrevPage 47 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