SOTAVerified

backdoor defense

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 131 papers

TitleStatusHype
Erasing Self-Supervised Learning Backdoor by Cluster Activation MaskingCode0
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed ModelsCode0
Cert-SSB: Toward Certified Sample-Specific Backdoor DefenseCode0
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial ExamplesCode0
Spy-Watermark: Robust Invisible Watermarking for Backdoor AttackCode0
FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious ClientsCode0
From Shortcuts to Triggers: Backdoor Defense with Denoised PoECode0
TERD: A Unified Framework for Safeguarding Diffusion Models Against BackdoorsCode0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored ModelsCode0
Towards Backdoor Stealthiness in Model Parameter SpaceCode0
CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset SeparationCode0
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs—0
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning—0
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations—0
Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis—0
Towards Understanding How Self-training Tolerates Data Backdoor Poisoning—0
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning—0
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness—0
WeDef: Weakly Supervised Backdoor Defense for Text Classification—0
Data-centric NLP Backdoor Defense from the Lens of Memorization—0
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks—0
A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models—0
Adversarial Backdoor Defense in CLIP—0
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.