SOTAVerified

backdoor defense

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 131 papers

TitleStatusHype
REFINE: Inversion-Free Backdoor Defense via Model ReprogrammingCode4
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based AgentsCode2
Clean-Label Backdoor Attacks on Video Recognition ModelsCode1
Backdoor Attacks for Remote Sensing Data with Wavelet TransformCode1
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor DefenseCode1
Backdoor Defense via Deconfounded Representation LearningCode1
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data PoisoningCode1
LIRA: Learnable, Imperceptible and Robust Backdoor AttacksCode1
Fisher Information guided Purification against Backdoor AttacksCode1
Effective Backdoor Defense by Exploiting Sensitivity of Poisoned SamplesCode1
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated LearningCode1
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning ParadigmsCode1
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace TrainingCode1
Reconstructive Neuron Pruning for Backdoor DefenseCode1
Backdoor Defense via Adaptively Splitting Poisoned DatasetCode1
Gracefully Filtering Backdoor Samples for Generative Large Language Models without RetrainingCode1
ONION: A Simple and Effective Defense Against Textual Backdoor AttacksCode1
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency RegularizationCode1
MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin StatisticCode1
Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph DistillationCode1
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor AttacksCode1
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationCode1
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace TrainingCode1
VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and PurificationCode1
FIBA: Frequency-Injection based Backdoor Attack in Medical Image AnalysisCode1
Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace SubnetworkCode1
Towards Probabilistic Verification of Machine UnlearningCode1
Backdoor Defense via Decoupling the Training ProcessCode1
Black-box Backdoor Defense via Zero-shot Image PurificationCode1
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack—0
Backdoor Defense through Self-Supervised and Generative Learning—0
BeniFul: Backdoor Defense via Middle Feature Analysis for Deep Neural Networks—0
BayBFed: Bayesian Backdoor Defense for Federated Learning—0
Backdoor defense, learnability and obfuscation—0
Adversarial Backdoor Defense in CLIP—0
Few-shot Backdoor Defense Using Shapley Estimation—0
Backdoor Defense in Federated Learning Using Differential Testing and Outlier Detection—0
Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire—0
Eliminating Backdoors in Neural Code Models for Secure Code Understanding—0
Backdoor Defense in Diffusion Models via Spatial Attention Unlearning—0
A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models—0
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks—0
Defense Against Syntactic Textual Backdoor Attacks with Token Substitution—0
Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons—0
Backdoor Defense with Machine Unlearning—0
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats—0
Backdoor Attack and Defense for Deep Regression—0
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning—0
Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection—0
Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks—0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.