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 371–380 of 523 papers

TitleStatusHype
RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNNCode0
Imperceptible and Robust Backdoor Attack in 3D Point CloudCode1
Link-Backdoor: Backdoor Attack on Link Prediction via Node InjectionCode0
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer—0
A Knowledge Distillation-Based Backdoor Attack in Federated Learning—0
FRIB: Low-poisoning Rate Invisible Backdoor Attack based on Feature Repair—0
Versatile Weight Attack via Flipping Limited BitsCode0
Technical Report: Assisting Backdoor Federated Learning with Whole Population Knowledge Alignment—0
Backdoor Attacks on Crowd CountingCode1
Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain—0
Show:102550
← PrevPage 38 of 53Next →

No leaderboard results yet.