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 1051–1075 of 1808 papers

TitleStatusHype
Restricted Black-box Adversarial Attack Against DeepFake Face Swapping—0
Boosting Adversarial Transferability of MLP-Mixer—0
Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacity—0
How Sampling Impacts the Robustness of Stochastic Neural Networks—0
Enhancing the Transferability via Feature-Momentum Adversarial Attack—0
A Mask-Based Adversarial Defense Scheme—0
Testing robustness of predictions of trained classifiers against naturally occurring perturbations—0
Metamorphic Testing-based Adversarial Attack to Fool Deepfake Detectors—0
UNBUS: Uncertainty-aware Deep Botnet Detection System in Presence of Perturbed Samples—0
Residue-Based Natural Language Adversarial Attack DetectionCode0
Homomorphic Encryption and Federated Learning based Privacy-Preserving CNN Training: COVID-19 Detection Use-Case—0
From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks—0
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization—0
Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning—0
SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition—0
Adversarial Neon Beam: A Light-based Physical Attack to DNNs—0
Zero-Query Transfer Attacks on Context-Aware Object Detectors—0
Exploring Frequency Adversarial Attacks for Face Forgery Detection—0
Boosting Black-Box Adversarial Attacks with Meta Learning—0
Text Adversarial Purification as Defense against Adversarial Attacks—0
A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies—0
Enhancing Transferability of Adversarial Examples with Spatial Momentum—0
Input-specific Attention Subnetworks for Adversarial Detection—0
Exploring High-Order Structure for Robust Graph Structure Learning—0
A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement—0
Show:102550
← PrevPage 43 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