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 161–170 of 523 papers

TitleStatusHype
Generalization Bound and New Algorithm for Clean-Label Backdoor AttackCode0
Whispers in Grammars: Injecting Covert Backdoors to Compromise Dense Retrieval SystemsCode0
CBD: A Certified Backdoor Detector Based on Local Dominant ProbabilityCode0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic ClassificationCode0
Adversarial Feature Map Pruning for BackdoorCode0
FooBaR: Fault Fooling Backdoor Attack on Neural Network TrainingCode0
Color Backdoor: A Robust Poisoning Attack in Color SpaceCode0
Going In Style: Audio Backdoors Through Stylistic TransformationsCode0
FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients InspectionCode0
Show:102550
← PrevPage 17 of 53Next →

No leaderboard results yet.