| Towards Backdoor Stealthiness in Model Parameter Space | Jan 10, 2025 | backdoor defensemodel | CodeCode Available | 0 |
| Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models | Jan 5, 2025 | backdoor defense | CodeCode Available | 0 |
| Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning | Dec 29, 2024 | backdoor defenseContrastive Learning | —Unverified | 0 |
| Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images | Dec 11, 2024 | Adversarial Defensebackdoor defense | —Unverified | 0 |
| Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining | Dec 3, 2024 | backdoor defenseComputational Efficiency | CodeCode Available | 1 |
| CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models | Dec 2, 2024 | backdoor defenseImage Generation | —Unverified | 0 |
| Neutralizing Backdoors through Information Conflicts for Large Language Models | Nov 27, 2024 | backdoor defense | —Unverified | 0 |
| MADE: Graph Backdoor Defense with Masked Unlearning | Nov 26, 2024 | backdoor defenseDrug Discovery | —Unverified | 0 |
| CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization | Nov 18, 2024 | backdoor defenseText Generation | CodeCode Available | 1 |
| BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation | Nov 17, 2024 | Action Recognitionbackdoor defense | CodeCode Available | 1 |
