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 501–523 of 523 papers

TitleStatusHype
SSDA: Secure Source-Free Domain AdaptationCode0
DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor AttackCode0
Energy Backdoor Attack to Deep Neural NetworksCode0
Whispers in Grammars: Injecting Covert Backdoors to Compromise Dense Retrieval SystemsCode0
Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated LearningCode0
EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding InspectionCode0
Versatile Weight Attack via Flipping Limited BitsCode0
Efficient Backdoor Attacks for Deep Neural Networks in Real-world ScenariosCode0
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion ModelsCode0
TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language ModelsCode0
Stealthy Backdoors as Compression ArtifactsCode0
AnywhereDoor: Multi-Target Backdoor Attacks on Object DetectionCode0
TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation ModelsCode0
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable TriggerCode0
Protocol-agnostic and Data-free Backdoor Attacks on Pre-trained Models in RF FingerprintingCode0
Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated LearningCode0
SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic TransferCode0
BagFlip: A Certified Defense against Data PoisoningCode0
Defending Neural Backdoors via Generative Distribution ModelingCode0
Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement LearningCode0
Defending against Insertion-based Textual Backdoor Attacks via AttributionCode0
UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion ModelsCode0
Defending Against Backdoor Attacks by Layer-wise Feature AnalysisCode0
Show:102550
← PrevPage 11 of 11Next →

No leaderboard results yet.