ShopBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multimodal Understanding | ShopBench | ShopFront Score73.8 | 18 | |
| Defense effectiveness against memory-mediated attacks | ShopBench-Agent | ASR-M8.3 | 10 | |
| Adversarial Attack on Memory-mediated Agents | ShopBench Agent | ASR-M82.3 | 6 | |
| Memory-mediated Attack Detection | ShopBench | ASR-M82.3 | 5 |
Showing 4 of 4 rows