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 1601–1650 of 1808 papers

TitleStatusHype
Investigating Decision Boundaries of Trained Neural Networks—0
MetaAdvDet: Towards Robust Detection of Evolving Adversarial AttacksCode0
A principled approach for generating adversarial images under non-smooth dissimilarity metricsCode0
Adversarial Self-Defense for Cycle-Consistent GANsCode0
A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding ModelsCode0
Exploring the Robustness of NMT Systems to Nonsensical Inputs—0
Black-box Adversarial ML Attack on Modulation Classification—0
Adversarial Attack on Sentiment Classification—0
Nonconvex Zeroth-Order Stochastic ADMM Methods with Lower Function Query Complexity—0
On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting MethodCode0
Natural Adversarial ExamplesCode1
Affine Disentangled GAN for Interpretable and Robust AV Perception—0
Adversarial Attacks in Sound Event Classification—0
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary AttackCode0
Generating Natural Language Adversarial Examples through Probability Weighted Word SaliencyCode0
Comment on "Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"—0
The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks—0
A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks—0
Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box AttacksCode0
Mimic and Fool: A Task Agnostic Adversarial AttackCode0
Provably Robust Deep Learning via Adversarially Trained Smoothed ClassifiersCode1
Adversarial Attack Generation Empowered by Min-Max OptimizationCode0
Robustness for Non-Parametric Classification: A Generic Attack and DefenseCode0
Efficient Project Gradient Descent for Ensemble Adversarial AttackCode0
Query-efficient Meta Attack to Deep Neural NetworksCode0
Should Adversarial Attacks Use Pixel p-Norm?—0
Architecture Selection via the Trade-off Between Accuracy and Robustness—0
Enhancing Transformation-based Defenses using a Distribution Classifier—0
Improving VAEs' Robustness to Adversarial Attack—0
Feature Space Perturbations Yield More Transferable Adversarial ExamplesCode0
Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and DefensesCode0
ShieldNets: Defending Against Adversarial Attacks Using Probabilistic Adversarial Robustness—0
Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial RobustnessCode0
Real-Time Adversarial AttacksCode0
Identifying Classes Susceptible to Adversarial Attacks—0
Bandlimiting Neural Networks Against Adversarial Attacks—0
Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness—0
Functional Adversarial AttacksCode0
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over SimplexCode0
Zeroth-Order Stochastic Alternating Direction Method of Multipliers for Nonconvex Nonsmooth Optimization—0
High Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksCode1
Scaleable input gradient regularization for adversarial robustnessCode0
Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object TrackingCode1
Thwarting finite difference adversarial attacks with output randomization—0
DoPa: A Comprehensive CNN Detection Methodology against Physical Adversarial Attacks—0
Taking Care of The Discretization Problem: A Comprehensive Study of the Discretization Problem and A Black-Box Adversarial Attack in Discrete Integer DomainCode0
A critique of the DeepSec Platform for Security Analysis of Deep Learning Models—0
Harnessing the Vulnerability of Latent Layers in Adversarially Trained ModelsCode0
Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent VariablesCode0
Interpreting and Evaluating Neural Network Robustness—0
Show:102550
← PrevPage 33 of 37Next →
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