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 411–420 of 523 papers

TitleStatusHype
Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class—0
Few-shot Backdoor Attacks via Neural Tangent KernelsCode0
Understanding Impacts of Task Similarity on Backdoor Attack and Detection—0
Where to Attack: A Dynamic Locator Model for Backdoor Attack in Text ClassificationsCode0
Defending Against Backdoor Attack on Graph Nerual Network by Explainability—0
FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning—0
Bidirectional Contrastive Split Learning for Visual Question Answering—0
RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNNCode0
Link-Backdoor: Backdoor Attack on Link Prediction via Node InjectionCode0
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer—0
Show:102550
← PrevPage 42 of 53Next →

No leaderboard results yet.