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

Showing 17261750 of 1808 papers

TitleStatusHype
Transferable and Configurable Audio Adversarial Attack from Low-Level Features0
The UCR Time Series ArchiveCode0
Is PGD-Adversarial Training Necessary? Alternative Training via a Soft-Quantization Network with Noisy-Natural Samples OnlyCode0
The Adversarial Attack and Detection under the Fisher Information MetricCode0
Improving the Generalization of Adversarial Training with Domain AdaptationCode0
CAAD 2018: Generating Transferable Adversarial ExamplesCode0
Universal Attacks on Equivariant Networks0
Using Word Embeddings to Explore the Learned Representations of Convolutional Neural Networks0
Adversarial Defense via Data Dependent Activation Function and Total Variation MinimizationCode0
Efficient Formal Safety Analysis of Neural NetworksCode0
Query-Efficient Black-Box Attack by Active Learning0
Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognition0
Certified Adversarial Robustness with Additive NoiseCode0
Query Attack via Opposite-Direction Feature:Towards Robust Image RetrievalCode0
IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detection0
Adversarial Attack Type I: Cheat Classifiers by Significant Changes0
Maximal Jacobian-based Saliency Map Attack0
Stochastic Combinatorial Ensembles for Defending Against Adversarial Examples0
Distributionally Adversarial AttackCode1
Structured Adversarial Attack: Towards General Implementation and Better InterpretabilityCode0
Rob-GAN: Generator, Discriminator, and Adversarial AttackerCode0
Evaluating and Understanding the Robustness of Adversarial Logit PairingCode0
Harmonic Adversarial Attack Method0
With Friends Like These, Who Needs Adversaries?Code0
A Game-Based Approximate Verification of Deep Neural Networks with Provable GuaranteesCode0
Show:102550
← PrevPage 70 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet20Test Accuracy89.9589.95(1)Community Verified
2Xu et al.Attack: PGD2078.68Unverified
33-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
4TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
5AdvTraining [madry2018]Attack: PGD2048.44Unverified
6TRADES [zhang2019b]Attack: PGD2045.9Unverified
7XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified