| Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning | May 7, 2023 | Backdoor Attackbackdoor defense | CodeCode Available | 1 |
| Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization | Apr 24, 2023 | backdoor defense | —Unverified | 0 |
| Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder | Mar 27, 2023 | backdoor defenseImage Generation | CodeCode Available | 0 |
| Backdoor Defense via Adaptively Splitting Poisoned Dataset | Mar 23, 2023 | backdoor defense | CodeCode Available | 1 |
| Black-box Backdoor Defense via Zero-shot Image Purification | Mar 21, 2023 | backdoor defense | CodeCode Available | 1 |
| Backdoor Defense via Deconfounded Representation Learning | Mar 13, 2023 | Backdoor Attackbackdoor defense | CodeCode Available | 1 |
| NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning | Mar 3, 2023 | backdoor defenseContrastive Learning | —Unverified | 0 |
| SATBA: An Invisible Backdoor Attack Based On Spatial Attention | Feb 25, 2023 | Backdoor Attackbackdoor defense | —Unverified | 0 |
| ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms | Feb 22, 2023 | backdoor defenseSelf-Supervised Learning | CodeCode Available | 1 |
| PECAN: A Deterministic Certified Defense Against Backdoor Attacks | Jan 27, 2023 | backdoor defenseimage-classification | —Unverified | 0 |
