backdoor defense

Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models ACL 2026 Batman: Benign Knowledge Alignment Through Malicious Null Space in Federated Backdoor Attack CVPR 2026 BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation AAAI 2026 CL-Guard: Defending DNNs Against Backdoors via Fine-Grained Neuron Analysis and Collaborative Dual-Network Learning AAAI 2026 DIFT: Protecting Contrastive Learning Against Data Poisoning Backdoor Attacks AAAI 2026 Logit-Margin Repulsion for Backdoor Defense CVPR 2026 MultiKD: Backdoor Defense in Federated Graph Learning via Attention-Guided Multi-Teacher Distillation AAAI 2026 SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs AAAI 2026 Adversarial-Inspired Backdoor Defense via Bridging Backdoor and Adversarial Attacks AAAI 2025 A Multi-Granularity Clustering Approach for Federated Backdoor Defense with the Adam Optimizer IJCAI 2025 Backdoor Defense via Enhanced Splitting and Trap Isolation ICCV 2025 Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models AAAI 2025 BadWindtunnel: Defending Backdoor in High-noise Simulated Training with Confidence Variance ACL 2025 CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks ICCV 2025 Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution EMNLP 2025 Data-centric NLP Backdoor Defense from the Lens of Memorization NAACL 2025 Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks CVPR 2025 Defending Against Repetitive Backdoor Attacks on Semi-Supervised Learning through Lens of Rate-Distortion-Perception Trade-Off WACV 2025 Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation ICCV 2025 Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation AAAI 2025 GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models IJCAI 2025 Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm NAACL 2025 Protecting against simultaneous data poisoning attacks ICLR 2025 Prototype Guided Backdoor Defense via Activation Space Manipulation ICCV 2025 REFINE: Inversion-Free Backdoor Defense via Model Reprogramming ICLR 2025