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 1226–1250 of 1808 papers

TitleStatusHype
A Differentiable Language Model Adversarial Attack on Text Classifiers—0
Examining the Human Perceptibility of Black-Box Adversarial Attacks on Face Recognition—0
Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features—0
Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based AttacksCode0
Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks—0
AdvFilter: Predictive Perturbation-aware Filtering against Adversarial Attack via Multi-domain Learning—0
Using BERT Encoding to Tackle the Mad-lib Attack in SMS Spam DetectionCode0
EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial AttacksCode0
Noise-based cyberattacks generating fake P300 waves in brain–computer interfacesCode0
Learning to Detect Adversarial Examples Based on Class Scores—0
Analytically Tractable Hidden-States Inference in Bayesian Neural Networks—0
DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural NetworksCode0
Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples—0
In-distribution adversarial attacks on object recognition models using gradient-free searchCode0
Bio-Inspired Adversarial Attack Against Deep Neural Networks—0
Attack Transferability Characterization for Adversarially Robust Multi-label ClassificationCode0
Feature Importance Guided Attack: A Model Agnostic Adversarial Attack—0
Attack to Fool and Explain Deep Networks—0
Limited Budget Adversarial Attack Against Online Image Stream—0
Light Lies: Optical Adversarial Attack—0
Is It Time to Redefine the Classification Task for Deep Learning Systems?—0
Strategically-timed State-Observation Attacks on Deep Reinforcement Learning Agents—0
Adversarial Interaction Attacks: Fooling AI to Misinterpret Human Intentions—0
Now You See It, Now You Dont: Adversarial Vulnerabilities in Computational Pathology—0
Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models—0
Show:102550
← PrevPage 50 of 73Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet20Test Acc90.190.1(1)Community Verified
2ResNet20Test Accuracy89.9589.95(1)Community Verified
3ResNet20Test Acc89.590.1(1)Community Verified
4Xu et al.Attack: PGD2078.68—Unverified
53-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
6TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
7AdvTraining [madry2018]Attack: PGD2048.44—Unverified
8TRADES [zhang2019b]Attack: PGD2045.9—Unverified
9XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet20Test Acc80.4—Community Verified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
3multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified