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 211–220 of 523 papers

TitleStatusHype
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning—0
DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-World—0
DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models—0
Does Few-shot Learning Suffer from Backdoor Attacks?—0
CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction—0
Double Landmines: Invisible Textual Backdoor Attacks based on Dual-Trigger—0
A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only—0
Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning—0
A4O: All Trigger for One sample—0
Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense—0
Show:102550
← PrevPage 22 of 53Next →

No leaderboard results yet.