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 1326–1350 of 1808 papers

TitleStatusHype
Real-World Adversarial Examples involving Makeup Application—0
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective—0
Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering—0
Text Adversarial Purification as Defense against Adversarial Attacks—0
Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack—0
Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements—0
Adversarial Attack with Raindrops—0
RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense—0
Redefining Machine Unlearning: A Conformal Prediction-Motivated Approach—0
Adaptive Local Adversarial Attacks on 3D Point Clouds for Augmented Reality—0
Refining Adaptive Zeroth-Order Optimization at Ease—0
Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples—0
Reinforce Attack: Adversarial Attack against BERT with Reinforcement Learning—0
Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models—0
ReLATE: Resilient Learner Selection for Multivariate Time-Series Classification Against Adversarial Attacks—0
Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models—0
Residue-Based Natural Language Adversarial Attack Detection—0
Transferable Adversarial Attack for Both Vision Transformers and Convolutional Networks via Momentum Integrated Gradients—0
Transferable Adversarial Attack on Image Tampering Localization—0
Resilient and constrained consensus against adversarial attacks: A distributed MPC framework—0
Resilient Dynamic Average Consensus based on Trusted agents—0
Resilient Learning-Based Control for Synchronization of Passive Multi-Agent Systems under Attack—0
Adaptive Adversarial Training Does Not Increase Recourse Costs—0
Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation—0
Restricted Black-box Adversarial Attack Against DeepFake Face Swapping—0
Show:102550
← PrevPage 54 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