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 151–200 of 523 papers

TitleStatusHype
Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via MotifsCode0
NoiseAttack: An Evasive Sample-Specific Multi-Targeted Backdoor Attack Through White Gaussian NoiseCode0
Model-Contrastive Learning for Backdoor DefenseCode0
MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger BridgesCode0
Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification TasksCode0
"No Matter What You Do": Purifying GNN Models via Backdoor UnlearningCode0
PBP: Post-training Backdoor Purification for Malware ClassifiersCode0
MDTD: A Multi Domain Trojan Detector for Deep Neural NetworksCode0
MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup TransferCode0
Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge ComputingCode0
Link-Backdoor: Backdoor Attack on Link Prediction via Node InjectionCode0
A general approach to enhance the survivability of backdoor attacks by decision path couplingCode0
Learning to Backdoor Federated LearningCode0
Mitigating Backdoor Attack by Injecting Proactive Defensive BackdoorCode0
Invisible Backdoor Triggers in Image Editing Model via Deep WatermarkingCode0
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identificationCode0
Claim-Guided Textual Backdoor Attack for Practical ApplicationsCode0
Color Backdoor: A Robust Poisoning Attack in Color SpaceCode0
Under-confidence Backdoors Are Resilient and Stealthy BackdoorsCode0
Backdoor Attack through Frequency DomainCode0
DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor AttackCode0
Whispers in Grammars: Injecting Covert Backdoors to Compromise Dense Retrieval SystemsCode0
How to Craft Backdoors with Unlabeled Data Alone?Code0
CBD: A Certified Backdoor Detector Based on Local Dominant ProbabilityCode0
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade DefenseCode0
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion ModelsCode0
Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic ClassificationCode0
Cross-Context Backdoor Attacks against Graph Prompt LearningCode0
Going In Style: Audio Backdoors Through Stylistic TransformationsCode0
MSDT: Masked Language Model Scoring Defense in Text DomainCode0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
Data Free Backdoor AttacksCode0
FooBaR: Fault Fooling Backdoor Attack on Neural Network TrainingCode0
AnywhereDoor: Multi-Target Backdoor Attacks on Object DetectionCode0
Generalization Bound and New Algorithm for Clean-Label Backdoor AttackCode0
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable TriggerCode0
Beating Backdoor Attack at Its Own GameCode0
AnywhereDoor: Multi-Target Backdoor Attacks on Object DetectionCode0
Enhancing Backdoor Attacks with Multi-Level MMD RegularizationCode0
Adversarial examples are useful too!Code0
Adversarial Feature Map Pruning for BackdoorCode0
FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients InspectionCode0
Few-shot Backdoor Attacks via Neural Tangent KernelsCode0
BagFlip: A Certified Defense against Data PoisoningCode0
Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural BackdoorCode0
Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion ModelsCode0
Backdoor Graph CondensationCode0
EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding InspectionCode0
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion ModelsCode0
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIPCode0
Show:102550
← PrevPage 4 of 11Next →

No leaderboard results yet.