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 421–430 of 523 papers

TitleStatusHype
Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning—0
CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks—0
DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning—0
Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World—0
DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs—0
Data Poisoning-based Backdoor Attack Framework against Supervised Learning Rules of Spiking Neural Networks—0
DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data—0
Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias—0
Deep Learning Backdoors—0
DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection—0
Show:102550
← PrevPage 43 of 53Next →

No leaderboard results yet.