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 1151–1175 of 1808 papers

TitleStatusHype
Input-specific Attention Subnetworks for Adversarial Detection—0
Towards Interpretability of Speech Pause in Dementia Detection using Adversarial Learning—0
Defense Against Explanation Manipulation—0
Adversarial Attack against Cross-lingual Knowledge Graph Alignment—0
An Actor-Critic Method for Simulation-Based Optimization—0
AdvCodeMix: Adversarial Attack on Code-Mixed Data—0
Disrupting Deep Uncertainty Estimation Without Harming AccuracyCode0
Generating Watermarked Adversarial Texts—0
Covariate Balancing Methods for Randomized Controlled Trials Are Not Adversarially Robust—0
Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations—0
Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning—0
Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information—0
Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction ModelsCode0
Adversarial Attacks on Gaussian Process BanditsCode0
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Meme Stock Prediction—0
Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools—0
Identification of Attack-Specific Signatures in Adversarial Examples—0
A Framework for Verification of Wasserstein Adversarial Robustness—0
Adversarial Attack across Datasets—0
Compressive Sensing Based Adaptive Defence Against Adversarial Images—0
EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware DetectionCode0
Adversarial Attack by Limited Point Cloud Surface Modifications—0
Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based VisionCode0
Reversible Attack based on Local Visual Adversarial Perturbation—0
A Uniform Framework for Anomaly Detection in Deep Neural NetworksCode0
Show:102550
← PrevPage 47 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