AgentPoison
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Backdoor Attack Detection | AgentPoison LLM Agent | Precision60 | 5 | |
| OOD Detection | AgentPoison (AP) | AUROC1 | 4 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Backdoor Attack Detection | AgentPoison LLM Agent | Precision60 | 5 | |
| OOD Detection | AgentPoison (AP) | AUROC1 | 4 |