SOTAVerified

backdoor defense

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 131 papers

TitleStatusHype
CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset SeparationCode0
CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks—0
InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning—0
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks—0
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs—0
Robust Anti-Backdoor Instruction Tuning in LVLMs—0
Spectral Insights into Data-Oblivious Critical Layers in Large Language Models—0
Heterogeneous Graph Backdoor Attack—0
FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious ClientsCode0
Cert-SSB: Toward Certified Sample-Specific Backdoor DefenseCode0
TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD DataCode0
Backdoor Defense in Diffusion Models via Spatial Attention Unlearning—0
Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks—0
Prototype Guided Backdoor Defense—0
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion ModelsCode0
A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models—0
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features—0
REFINE: Inversion-Free Backdoor Defense via Model ReprogrammingCode4
Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognition—0
PCAP-Backdoor: Backdoor Poisoning Generator for Network Traffic in CPS/IoT Environments—0
Towards Backdoor Stealthiness in Model Parameter SpaceCode0
Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language ModelsCode0
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning—0
Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images—0
Gracefully Filtering Backdoor Samples for Generative Large Language Models without RetrainingCode1
CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models—0
Neutralizing Backdoors through Information Conflicts for Large Language Models—0
MADE: Graph Backdoor Defense with Masked Unlearning—0
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency RegularizationCode1
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationCode1
FedBlock: A Blockchain Approach to Federated Learning against Backdoor Attacks—0
Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection—0
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed ModelsCode0
BeniFul: Backdoor Defense via Middle Feature Analysis for Deep Neural Networks—0
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor DefenseCode1
"No Matter What You Do": Purifying GNN Models via Backdoor UnlearningCode0
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats—0
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning—0
Adversarial Backdoor Defense in CLIP—0
Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis—0
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning ParadigmCode0
Data-centric NLP Backdoor Defense from the Lens of Memorization—0
PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models—0
TERD: A Unified Framework for Safeguarding Diffusion Models Against BackdoorsCode0
Backdoor defense, learnability and obfuscation—0
Backdoor Defense through Self-Supervised and Generative Learning—0
Fisher Information guided Purification against Backdoor AttacksCode1
VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and PurificationCode1
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation—0
Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor AttacksCode0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.