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 1371–1380 of 1808 papers

Title	Date	Tasks	Status	Hype
Dynamic backdoor attacks against federated learning	Nov 15, 2020	Adversarial AttackBIG-bench Machine Learning	—Unverified	0
Fooling the primate brain with minimal, targeted image manipulation	Nov 11, 2020	Adversarial AttackImage Manipulation	—Unverified	0
Efficient and Transferable Adversarial Examples from Bayesian Neural Networks	Nov 10, 2020	Adversarial AttackBayesian Inference	CodeCode Available	0
Bridging the Performance Gap between FGSM and PGD Adversarial Training	Nov 7, 2020	Adversarial AttackAdversarial Robustness	CodeCode Available	0
Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty	Nov 5, 2020	Adversarial AttackBenchmarking	CodeCode Available	0
Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks	Nov 5, 2020	Adversarial Attack	—Unverified	0
Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGA	Nov 5, 2020	Adversarial AttackCloud Computing	CodeCode Available	0
Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks	Nov 3, 2020	Adversarial AttackMachine Translation	CodeCode Available	0
Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries	Nov 1, 2020	Adversarial AttackDeep Learning	—Unverified	0
Generalization to Mitigate Synonym Substitution Attacks	Nov 1, 2020	Adversarial Attack	—Unverified	0

Show:10 25 50

← PrevPage 138 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