| CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization | Nov 18, 2024 | backdoor defenseText Generation | CodeCode Available | 1 | 5 |
| ONION: A Simple and Effective Defense Against Textual Backdoor Attacks | Nov 20, 2020 | Backdoor Attackbackdoor defense | CodeCode Available | 1 | 5 |
| VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification | Aug 28, 2024 | Anomaly Detectionbackdoor defense | CodeCode Available | 1 | 5 |
| Black-box Backdoor Defense via Zero-shot Image Purification | Mar 21, 2023 | backdoor defense | CodeCode Available | 1 | 5 |
| DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor Attack | Aug 18, 2023 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
| Progressive Poisoned Data Isolation for Training-time Backdoor Defense | Dec 20, 2023 | backdoor defenseData Poisoning | CodeCode Available | 0 | 5 |
| OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection | Dec 4, 2023 | Anomaly Detectionbackdoor defense | CodeCode Available | 0 | 5 |
| "No Matter What You Do": Purifying GNN Models via Backdoor Unlearning | Oct 2, 2024 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
| BadActs: A Universal Backdoor Defense in the Activation Space | May 18, 2024 | backdoor defense | CodeCode Available | 0 | 5 |
| Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models | Jan 5, 2025 | backdoor defense | CodeCode Available | 0 | 5 |
| MSDT: Masked Language Model Scoring Defense in Text Domain | Nov 10, 2022 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
| Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor | May 25, 2024 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
| Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder | Mar 27, 2023 | backdoor defenseImage Generation | CodeCode Available | 0 | 5 |
| Model-Contrastive Learning for Backdoor Defense | May 9, 2022 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
| Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features | Jun 29, 2023 | backdoor defense | CodeCode Available | 0 | 5 |
| Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples | Jul 20, 2023 | backdoor defense | CodeCode Available | 0 | 5 |
| Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models | Feb 28, 2025 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
| Beating Backdoor Attack at Its Own Game | Jul 28, 2023 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
| From Shortcuts to Triggers: Backdoor Defense with Denoised PoE | May 24, 2023 | backdoor defenseData Poisoning | CodeCode Available | 0 | 5 |
| Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks | Aug 28, 2024 | backdoor defense | CodeCode Available | 0 | 5 |
| Efficient Backdoor Removal Through Natural Gradient Fine-tuning | Jun 30, 2023 | backdoor defense | CodeCode Available | 0 | 5 |
| Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency | Mar 15, 2024 | backdoor defense | CodeCode Available | 0 | 5 |
| From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models | Nov 4, 2023 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
| Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm | Sep 21, 2024 | backdoor defenseparameter-efficient fine-tuning | CodeCode Available | 0 | 5 |
| Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models | Jul 31, 2024 | Backdoor Attackbackdoor defense | CodeCode Available | 0 | 5 |
