backdoor defense

54 papers

Explore in graph

Co-occurring keywords

backdoor attack (377) adversarial learning (1592) neural network (6616) data poisoning (128) model security (118) deep neural network (1801) adversarial defense (324) model purification (7) trigger detection (28) neural network security (46)

Papers

BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation AAAI 2026

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs AAAI 2026

MultiKD: Backdoor Defense in Federated Graph Learning via Attention-Guided Multi-Teacher 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

Adversarial-Inspired Backdoor Defense via Bridging Backdoor and Adversarial Attacks AAAI 2025

Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution EMNLP 2025

Sanitizing Backdoored Graph Neural Networks: A Multidimensional Approach IJCAI 2025

Universal Backdoor Defense via Label Consistency in Vertical Federated Learning IJCAI 2025

Prototype Guided Backdoor Defense via Activation Space Manipulation ICCV 2025

Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor AAAI 2025

Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks CVPR 2025

A Multi-Granularity Clustering Approach for Federated Backdoor Defense with the Adam Optimizer IJCAI 2025

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models AAAI 2025

CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks ICCV 2025

GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models IJCAI 2025

Data-centric NLP Backdoor Defense from the Lens of Memorization NAACL 2025

Defending Against Repetitive Backdoor Attacks on Semi-Supervised Learning through Lens of Rate-Distortion-Perception Trade-Off WACV 2025

BadWindtunnel: Defending Backdoor in High-noise Simulated Training with Confidence Variance ACL 2025

Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm NAACL 2025

Spectral Insights into Data-Oblivious Critical Layers in Large Language Models ACL 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

Backdoor Defense via Enhanced Splitting and Trap Isolation ICCV 2025

Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024