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 351–360 of 523 papers

TitleStatusHype
Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks—0
Attack On Prompt: Backdoor Attack in Prompt-Based Continual Learning—0
Backdoor Attack in the Physical World—0
Backdoor Attack on Multilingual Machine Translation—0
Backdoor Attack on Vertical Federated Graph Neural Network Learning—0
Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation—0
Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger—0
Backdoor Attacks against Image-to-Image Networks—0
Backdoor Attacks Against Incremental Learners: An Empirical Evaluation Study—0
Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions—0
Show:102550
← PrevPage 36 of 53Next →

No leaderboard results yet.