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

Showing 121130 of 523 papers

TitleStatusHype
BadDet: Backdoor Attacks on Object DetectionCode0
Learning to Backdoor Federated LearningCode0
Backdoor Attack against One-Class Sequential Anomaly Detection ModelsCode0
Towards Adversarial Robustness And Backdoor Mitigation in SSLCode0
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identificationCode0
Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge ComputingCode0
Attacking by Aligning: Clean-Label Backdoor Attacks on Object DetectionCode0
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade DefenseCode0
How to Craft Backdoors with Unlabeled Data Alone?Code0
Going In Style: Audio Backdoors Through Stylistic TransformationsCode0
Show:102550
← PrevPage 13 of 53Next →

No leaderboard results yet.