SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1576–1600 of 1808 papers

TitleStatusHype
ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness—0
Real-world adversarial attack on MTCNN face detection systemCode0
On Robustness of Neural Ordinary Differential EquationsCode0
Learning deep forest with multi-scale Local Binary Pattern features for face anti-spoofing—0
Adversarial Learning of Deepfakes in Accounting—0
AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation—0
Yet another but more efficient black-box adversarial attack: tiling and evolution strategies—0
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural NetworksCode0
Perturbations are not Enough: Generating Adversarial Examples with Spatial Distortions—0
An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack—0
Role of Spatial Context in Adversarial Robustness for Object DetectionCode0
Deep k-NN Defense against Clean-label Data Poisoning AttacksCode0
Towards Certified Defense for Unrestricted Adversarial Attacks—0
Simple and Effective Stochastic Neural Networks—0
Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection—0
Learning Key Steps to Attack Deep Reinforcement Learning Agents—0
Adversarial training with perturbation generator networks—0
Towards A Unified Min-Max Framework for Adversarial Exploration and Robustness—0
DO-AutoEncoder: Learning and Intervening Bivariate Causal Mechanisms in Images—0
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over the Simplex—0
THE EFFECT OF ADVERSARIAL TRAINING: A THEORETICAL CHARACTERIZATION—0
SELF-KNOWLEDGE DISTILLATION ADVERSARIAL ATTACK—0
Universal Adversarial Attack Using Very Few Test Examples—0
Defending Against Adversarial Examples by Regularized Deep Embedding—0
Robust saliency maps with distribution-preserving decoys—0
Show:102550
← PrevPage 64 of 73Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68—Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
4AdvTraining [madry2018]Attack: PGD2048.44—Unverified
5TRADES [zhang2019b]Attack: PGD2045.9—Unverified
6XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified