backdoor defense

Sanitizing Backdoored Graph Neural Networks: A Multidimensional Approach IJCAI 2025 Spectral Insights into Data-Oblivious Critical Layers in Large Language Models ACL 2025 Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor AAAI 2025 Universal Backdoor Defense via Label Consistency in Vertical Federated Learning IJCAI 2025 Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space ACL 2024 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 BadActs: A Universal Backdoor Defense in the Activation Space ACL 2024 Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack NeurIPS 2024 From Shortcuts to Triggers: Backdoor Defense with Denoised PoE NAACL 2024 LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect NeurIPS 2024 Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor NeurIPS 2024 PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification AAAI 2024 SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification NeurIPS 2024 Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense NeurIPS 2024 Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness NeurIPS 2024 Backdoor Cleansing With Unlabeled Data CVPR 2023 Backdoor Defense via Adaptively Splitting Poisoned Dataset CVPR 2023 Backdoor Defense via Deconfounded Representation Learning CVPR 2023 Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization ICCV 2023 Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features NeurIPS 2023 On the Vulnerability of Backdoor Defenses for Federated Learning AAAI 2023 Reconstructive Neuron Pruning for Backdoor Defense ICML 2023 Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples NeurIPS 2023 Single Image Backdoor Inversion via Robust Smoothed Classifiers CVPR 2023 TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models ICCV 2023