SOTAVerified

backdoor defense

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 131 papers

TitleStatusHype
SAB:A Stealing and Robust Backdoor Attack based on Steganographic Algorithm against Federated Learning—0
Protecting against simultaneous data poisoning attacks—0
Eliminating Backdoors in Neural Code Models for Secure Code Understanding—0
Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion ModelsCode0
Model-agnostic clean-label backdoor mitigation in cybersecurity environments—0
Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense—0
Defense Against Syntactic Textual Backdoor Attacks with Token Substitution—0
Robustness Inspired Graph Backdoor Defense—0
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness—0
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective—0
Magnitude-based Neuron Pruning for Backdoor Defens—0
Towards Unified Robustness Against Both Backdoor and Adversarial AttacksCode0
Mitigating Backdoor Attack by Injecting Proactive Defensive BackdoorCode0
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack—0
Interactive Simulations of Backdoors in Neural Networks—0
BadActs: A Universal Backdoor Defense in the Activation SpaceCode0
LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning—0
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning—0
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction ConsistencyCode0
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based AgentsCode2
Spy-Watermark: Robust Invisible Watermarking for Backdoor AttackCode0
Backdoor Defense via Test-Time Detecting and Repairing—0
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?—0
Progressive Poisoned Data Isolation for Training-time Backdoor DefenseCode0
Erasing Self-Supervised Learning Backdoor by Cluster Activation MaskingCode0
OCGEC: One-class Graph Embedding Classification for DNN Backdoor DetectionCode0
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations—0
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion ModelsCode0
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace TrainingCode1
Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace TrainingCode1
DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor AttackCode0
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored ModelsCode0
Beating Backdoor Attack at Its Own GameCode0
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial ExamplesCode0
Fedward: Flexible Federated Backdoor Defense Framework with Non-IID Data—0
Efficient Backdoor Removal Through Natural Gradient Fine-tuningCode0
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned FeaturesCode0
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers—0
From Shortcuts to Triggers: Backdoor Defense with Denoised PoECode0
Reconstructive Neuron Pruning for Backdoor DefenseCode1
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data PoisoningCode1
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization—0
Mask and Restore: Blind Backdoor Defense at Test Time with Masked AutoencoderCode0
Backdoor Defense via Adaptively Splitting Poisoned DatasetCode1
Black-box Backdoor Defense via Zero-shot Image PurificationCode1
Backdoor Defense via Deconfounded Representation LearningCode1
NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning—0
SATBA: An Invisible Backdoor Attack Based On Spatial Attention—0
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning ParadigmsCode1
PECAN: A Deterministic Certified Defense Against Backdoor Attacks—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.