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 461–470 of 523 papers

TitleStatusHype
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
Backdoor Attack with Imperceptible Input and Latent Modification—0
Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated LearningCode0
Backdoor Attack through Frequency DomainCode0
DBIA: Data-free Backdoor Injection Attack against Transformer NetworksCode0
An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences—0
Enhancing Backdoor Attacks with Multi-Level MMD RegularizationCode0
Backdoor Pre-trained Models Can Transfer to AllCode0
Widen The Backdoor To Let More Attackers In—0
Show:102550
← PrevPage 47 of 53Next →

No leaderboard results yet.