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 341–350 of 523 papers

TitleStatusHype
Robust Backdoor Attacks against Deep Neural Networks in Real Physical World—0
Robust Backdoor Attacks on Object Detection in Real World—0
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers—0
SAB:A Stealing and Robust Backdoor Attack based on Steganographic Algorithm against Federated Learning—0
SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning—0
SATBA: An Invisible Backdoor Attack Based On Spatial Attention—0
Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments—0
Securing Federated Learning against Backdoor Threats with Foundation Model Integration—0
Manipulating and Mitigating Generative Model Biases without Retraining—0
SFIBA: Spatial-based Full-target Invisible Backdoor Attacks—0
Show:102550
← PrevPage 35 of 53Next →

No leaderboard results yet.