| Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations | Nov 16, 2023 | backdoor defense | —Unverified | 0 |
| Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis | Sep 24, 2024 | backdoor defenseObject | —Unverified | 0 |
| Towards Understanding How Self-training Tolerates Data Backdoor Poisoning | Jan 20, 2023 | backdoor defenseRepresentation Learning | —Unverified | 0 |
| Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning | Mar 24, 2024 | backdoor defenseContrastive Learning | —Unverified | 0 |
| Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness | May 30, 2024 | backdoor defense | —Unverified | 0 |
| Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation | Aug 28, 2024 | backdoor defense | —Unverified | 0 |
| Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognition | Feb 3, 2025 | Automatic Speech Recognitionbackdoor defense | —Unverified | 0 |
| Heterogeneous Graph Backdoor Attack | May 30, 2025 | Backdoor Attackbackdoor defense | —Unverified | 0 |
| Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks | Jan 31, 2022 | Backdoor Attackbackdoor defense | —Unverified | 0 |
| From Shortcuts to Triggers: Backdoor Defense with Denoised PoE | May 24, 2023 | backdoor defenseData Poisoning | CodeCode Available | 0 |
