SOTAVerified

Backdoor Attack

Backdoor attacks inject maliciously constructed data into a training set so that, at test time, the trained model misclassifies inputs patched with a backdoor trigger as an adversarially-desired target class.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 421–430 of 523 papers

TitleStatusHype
Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing—0
Compression-Resistant Backdoor Attack against Deep Neural Networks—0
DEFEAT: Deep Hidden Feature Backdoor Attacks by Imperceptible Perturbation and Latent Representation Constraints—0
Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks—0
FIBA: Frequency-Injection based Backdoor Attack in Medical Image AnalysisCode1
Backdoor Attack with Imperceptible Input and Latent Modification—0
Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated LearningCode0
Towards Practical Deployment-Stage Backdoor Attack on Deep Neural NetworksCode1
DBIA: Data-free Backdoor Injection Attack against Transformer NetworksCode0
Backdoor Attack through Frequency DomainCode0
Show:102550
← PrevPage 43 of 53Next →

No leaderboard results yet.