Unintended Attack Detection on Financial Agent Dialogues
85.71Unintended Attack F1FinSec
Evaluation Results
| Method | Links | |
|---|---|---|
| FinSec2026.04 | 85.71 | |
| FinO3adv2026.04 | 81.82 | |
| O3 (R-Judge)2026.04 | 80 | |
| FinO32026.04 | 73.68 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| FinSec2026.04 | 85.71 | |
| FinO3adv2026.04 | 81.82 | |
| O3 (R-Judge)2026.04 | 80 | |
| FinO32026.04 | 73.68 |