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 251–260 of 523 papers

TitleStatusHype
Prompt Backdoors in Visual Prompt Learning—0
Moiré Backdoor Attack (MBA): A Novel Trigger for Pedestrian Detectors in the Physical World—0
GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning—0
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade DefenseCode0
VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language ModelsCode1
Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic ClassificationCode0
Robust Backdoor Attacks on Object Detection in Real World—0
Physical Invisible Backdoor Based on Camera Imaging—0
MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems—0
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System—0
Show:102550
← PrevPage 26 of 53Next →

No leaderboard results yet.