| CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation | Jul 7, 2025 | backdoor defense | CodeCode Available | 0 |
| CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks | Jun 20, 2025 | Backdoor Attackbackdoor defense | —Unverified | 0 |
| InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning | Jun 14, 2025 | backdoor defenseContrastive Learning | —Unverified | 0 |
| TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks | Jun 12, 2025 | backdoor defenseData Poisoning | —Unverified | 0 |
| SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs | Jun 5, 2025 | backdoor defenseImage Captioning | —Unverified | 0 |
| Robust Anti-Backdoor Instruction Tuning in LVLMs | Jun 4, 2025 | backdoor defenseInstruction Following | —Unverified | 0 |
| Spectral Insights into Data-Oblivious Critical Layers in Large Language Models | May 31, 2025 | backdoor defenseDomain Adaptation | —Unverified | 0 |
| Heterogeneous Graph Backdoor Attack | May 30, 2025 | Backdoor Attackbackdoor defense | —Unverified | 0 |
| FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients | May 17, 2025 | backdoor defenseFederated Learning | CodeCode Available | 0 |
| Cert-SSB: Toward Certified Sample-Specific Backdoor Defense | Apr 30, 2025 | backdoor defense | CodeCode Available | 0 |
