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 11–20 of 523 papers

TitleStatusHype
Poison in the Well: Feature Embedding Disruption in Backdoor Attacks—0
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers—0
BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World—0
BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization—0
FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition—0
Defending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning—0
MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger BridgesCode0
Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving—0
BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models—0
Protocol-agnostic and Data-free Backdoor Attacks on Pre-trained Models in RF FingerprintingCode0
Show:102550
← PrevPage 2 of 53Next →

No leaderboard results yet.