SOTAVerified

backdoor defense

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–75 of 131 papers

TitleStatusHype
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack—0
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features—0
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer—0
CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models—0
CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks—0
Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks—0
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning—0
Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons—0
Defense Against Syntactic Textual Backdoor Attacks with Token Substitution—0
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats—0
Eliminating Backdoors in Neural Code Models for Secure Code Understanding—0
Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection—0
Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers—0
Heterogeneous Graph Backdoor Attack—0
Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks—0
Interactive Simulations of Backdoors in Neural Networks—0
InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning—0
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?—0
LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning—0
MADE: Graph Backdoor Defense with Masked Unlearning—0
Magnitude-based Neuron Pruning for Backdoor Defens—0
Model-agnostic clean-label backdoor mitigation in cybersecurity environments—0
NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning—0
Neutralizing Backdoors through Information Conflicts for Large Language Models—0
On Provable Backdoor Defense in Collaborative Learning—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.