SOTAVerified

backdoor defense

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–131 of 131 papers

TitleStatusHype
Progressive Poisoned Data Isolation for Training-time Backdoor DefenseCode0
FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious ClientsCode0
TERD: A Unified Framework for Safeguarding Diffusion Models Against BackdoorsCode0
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion ModelsCode0
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning ParadigmCode0
Cert-SSB: Toward Certified Sample-Specific Backdoor DefenseCode0
CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset SeparationCode0
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored ModelsCode0
Towards Backdoor Stealthiness in Model Parameter SpaceCode0
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed ModelsCode0
Erasing Self-Supervised Learning Backdoor by Cluster Activation MaskingCode0
Efficient Backdoor Removal Through Natural Gradient Fine-tuningCode0
BadActs: A Universal Backdoor Defense in the Activation SpaceCode0
Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion ModelsCode0
Backdoor Defense via Suppressing Model ShortcutsCode0
Mask and Restore: Blind Backdoor Defense at Test Time with Masked AutoencoderCode0
Mitigating Backdoor Attack by Injecting Proactive Defensive BackdoorCode0
Towards Unified Robustness Against Both Backdoor and Adversarial AttacksCode0
Model-Contrastive Learning for Backdoor DefenseCode0
MSDT: Masked Language Model Scoring Defense in Text DomainCode0
Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language ModelsCode0
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned FeaturesCode0
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial ExamplesCode0
"No Matter What You Do": Purifying GNN Models via Backdoor UnlearningCode0
OCGEC: One-class Graph Embedding Classification for DNN Backdoor DetectionCode0
Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor AttacksCode0
TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD DataCode0
Spy-Watermark: Robust Invisible Watermarking for Backdoor AttackCode0
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction ConsistencyCode0
DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor AttackCode0
Beating Backdoor Attack at Its Own GameCode0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.