| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| StrongREJECT | DualEdit | ASR (w/ trigger)0.601 | 18 | 3mo ago | |
| Legislative Drafting | RareBN | ASR100 | 10 | 1mo ago | |
| Software Engineering | PAB | ASR95 | 8 | 1mo ago | |
| CALISA | TEMPO-Diffusion | Vicn Success Rate (c)18.4 | 6 | 1mo ago | |
| GTSRB | TEMPO-Diffusion | Vicnc22.3 | 6 | 1mo ago | |
| CIFAR10 | TEMPO-Diffusion | Vicinity (nc)28.5 | 6 | 1mo ago | |
| nuScenes | BadDreamer | WM-ASR92.5 | 6 | 1mo ago | |
| Healthcare Advice | PAB | AIR88 | 5 | 1mo ago | |
| SD-Prompts Phrase trigger (in-domain) | AEWC | ASR (τ=0.85)99 | 4 | 2mo ago | |
| SD-Prompts Unicode trigger (in-domain) | AEWC | ASR (τ=0.85)98.7 | 4 | 2mo ago | |
| SD-Prompts Syntactic trigger (in-domain) | ASR ($ au=0.85$)99.1 | 4 | 2mo ago | ||
| ImageNet 100-B | CorruptEncoder | ASR0.899 | 3 | 5mo ago |