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 1201–1225 of 1808 papers

TitleStatusHype
A Survey On Universal Adversarial AttackCode1
Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial TrainingCode0
Model-Agnostic Defense for Lane Detection against Adversarial AttackCode0
Fast Minimum-norm Adversarial Attacks through Adaptive Norm ConstraintsCode2
Graphfool: Targeted Label Adversarial Attack on Graph Embedding—0
Targeted Attack against Deep Neural Networks via Flipping Limited Weight BitsCode1
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-LearningCode1
Fortify Machine Learning Production Systems: Detect and Classify Adversarial Attacks—0
CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification—0
Certifiably Robust Variational Autoencoders—0
Adversarial Attack on Network Embeddings via Supervised Network PoisoningCode0
Adversarially robust deepfake media detection using fused convolutional neural network predictions—0
Enhancing Real-World Adversarial Patches through 3D Modeling of Complex Target ScenesCode0
RoBIC: A benchmark suite for assessing classifiers robustnessCode0
Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples—0
Audio Adversarial Examples: Attacks Using Vocal Masks—0
Improving Neural Network Robustness through Neighborhood Preserving Layers—0
Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models—0
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems—0
Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) methodCode0
Towards Practical Robustness Analysis for DNNs based on PAC-Model LearningCode0
Generating Black-Box Adversarial Examples in Sparse Domain—0
Robust Reinforcement Learning on State Observations with Learned Optimal AdversaryCode1
PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack—0
Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization—0
Show:102550
← PrevPage 49 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