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 261–270 of 523 papers

TitleStatusHype
EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events—0
FTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learning—0
Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack—0
MDTD: A Multi Domain Trojan Detector for Deep Neural NetworksCode0
PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model ModificationCode1
Protect Federated Learning Against Backdoor Attacks via Data-Free Trigger Generation—0
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition—0
DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor AttackCode0
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers—0
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt InjectionCode1
Show:102550
← PrevPage 27 of 53Next →

No leaderboard results yet.