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 976–1000 of 1808 papers

TitleStatusHype
Robust Constrained Reinforcement Learning—0
Robust Deep Learning Models Against Semantic-Preserving Adversarial Attack—0
Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks—0
Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey—0
Robust Ensemble Model Training via Random Layer Sampling Against Adversarial Attack—0
Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks—0
Robustness of Explanation Methods for NLP Models—0
Testing robustness of predictions of trained classifiers against naturally occurring perturbations—0
Robustness of Selected Learning Models under Label-Flipping Attack—0
Robust Optimal Power Flow Against Adversarial Attacks: A Tri-Level Optimization Approach—0
Robust Physical-World Attacks on Face Recognition—0
Robust saliency maps with distribution-preserving decoys—0
SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition—0
Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness—0
Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack—0
Robust Superpixel-Guided Attentional Adversarial Attack—0
Robust Text CAPTCHAs Using Adversarial Examples—0
Robust Transfer Learning with Pretrained Language Models through Adapters—0
Robust Unpaired Single Image Super-Resolution of Faces—0
Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective—0
Rogue Cell: Adversarial Attack and Defense in Untrusted O-RAN Setup Exploiting the Traffic Steering xApp—0
ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints—0
SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation—0
SAD: Saliency-based Defenses Against Adversarial Examples—0
Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors—0
Show:102550
← PrevPage 40 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