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 901–925 of 1808 papers

TitleStatusHype
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
Efficient Neural Network Analysis with Sum-of-InfeasibilitiesCode2
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and DefenseCode0
Alleviating Adversarial Attacks on Variational Autoencoders with MCMCCode1
RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression—0
AutoAdversary: A Pixel Pruning Method for Sparse Adversarial Attack—0
DTA: Physical Camouflage Attacks using Differentiable Transformation Network—0
Defending Against Adversarial Attack in ECG Classification with Adversarial Distillation Training—0
Efficient universal shuffle attack for visual object tracking—0
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacksCode1
Block-Sparse Adversarial Attack to Fool Transformer-Based Text ClassifiersCode0
Frequency-driven Imperceptible Adversarial Attack on Semantic SimilarityCode1
Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems—0
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural PhenomenonCode1
Art-Attack: Black-Box Adversarial Attack via Evolutionary Art—0
A^3D: A Platform of Searching for Robust Neural Architectures and Efficient Adversarial Attacks—0
Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV TrackingCode1
Adversarial attacks on neural networks through canonical Riemannian foliationsCode0
Detecting Adversarial Perturbations in Multi-Task PerceptionCode0
Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey—0
Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias—0
Critical Checkpoints for Evaluating Defence Models Against Adversarial Attack and Robustness—0
Generative Adversarial Network-Driven Detection of Adversarial Tasks in Mobile Crowdsensing—0
Show:102550
← PrevPage 37 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