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 1426–1450 of 1808 papers

TitleStatusHype
Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses—0
A New Perspective on Stabilizing GANs training: Direct Adversarial TrainingCode0
Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization—0
Improving adversarial robustness of deep neural networks by using semantic information—0
Model Robustness with Text Classification: Semantic-preserving adversarial attacks—0
FireBERT: Hardening BERT-based classifiers against adversarial attackCode0
Visual Attack and Defense on Text—0
Stabilizing Deep Tomographic Reconstruction—0
Hardware Accelerator for Adversarial Attacks on Deep Learning Neural Networks—0
Physical Adversarial Attack on Vehicle Detector in the Carla Simulator—0
DeepPeep: Exploiting Design Ramifications to Decipher the Architecture of Compact DNNs—0
Adversarial Robustness for Machine Learning Cyber Defenses Using Log Data—0
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning—0
Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing—0
From Sound Representation to Model Robustness—0
Adversarial Privacy-preserving FilterCode0
T-BFA: Targeted Bit-Flip Adversarial Weight AttackCode0
Exploiting vulnerabilities of deep neural networks for privacy protectionCode0
DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection—0
Anomaly Detection in Unsupervised Surveillance Setting Using Ensemble of Multimodal Data with Adversarial Defense—0
Accelerated Stochastic Gradient-free and Projection-free MethodsCode0
Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack—0
Generating Adversarial Inputs Using A Black-box Differential Technique—0
Evaluation of Adversarial Training on Different Types of Neural Networks in Deep Learning-based IDSs—0
On Data Augmentation and Adversarial Risk: An Empirical Analysis—0
Show:102550
← PrevPage 58 of 73Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet20Test Accuracy89.9589.95(1)Community Verified
2Xu et al.Attack: PGD2078.68—Unverified
33-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
4TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
5AdvTraining [madry2018]Attack: PGD2048.44—Unverified
6TRADES [zhang2019b]Attack: PGD2045.9—Unverified
7XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified