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 141–150 of 523 papers

TitleStatusHype
Backdooring Bias into Text-to-Image ModelsCode0
Under-confidence Backdoors Are Resilient and Stealthy BackdoorsCode0
Mitigating Backdoor Attack by Injecting Proactive Defensive BackdoorCode0
PBP: Post-training Backdoor Purification for Malware ClassifiersCode0
Enhancing Backdoor Attacks with Multi-Level MMD RegularizationCode0
Beating Backdoor Attack at Its Own GameCode0
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion ModelsCode0
Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic ClassificationCode0
Going In Style: Audio Backdoors Through Stylistic TransformationsCode0
Generalization Bound and New Algorithm for Clean-Label Backdoor AttackCode0
Show:102550
← PrevPage 15 of 53Next →

No leaderboard results yet.