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 1376–1400 of 1808 papers

TitleStatusHype
Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks—0
Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGACode0
Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial AttacksCode0
Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries—0
Generalization to Mitigate Synonym Substitution Attacks—0
Second-Order NLP Adversarial Examples—0
TextAttack: Lessons learned in designing Python frameworks for NLP—0
Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification—0
Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?—0
Defense-guided Transferable Adversarial Attacks—0
Rewriting Meaningful Sentences via Conditional BERT Sampling and an application on fooling text classifiers—0
Learning Black-Box Attackers with Transferable Priors and Query FeedbackCode0
L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set—0
A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning—0
Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing—0
Explain2Attack: Text Adversarial Attacks via Cross-Domain InterpretabilityCode0
An Evasion Attack against Stacked Capsule AutoencoderCode0
GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial AttackCode0
An Analysis of Robustness of Non-Lipschitz NetworksCode0
Learning to Attack with Fewer Pixels: A Probabilistic Post-hoc Framework for Refining Arbitrary Dense Adversarial Attacks—0
EFSG: Evolutionary Fooling Sentences Generator—0
Learning Task-aware Robust Deep Learning Systems—0
Adversarial Attacks to Machine Learning-Based Smart Healthcare Systems—0
Adversarial attacks on audio source separation—0
Adversarial Patch Attacks on Monocular Depth Estimation Networks—0
Show:102550
← PrevPage 56 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