Output Stealthiness Assessment on Token Forcing (TF) attack
100Delivery Rate (DR)IF-SFT
Evaluation Results
| Method | Links | |
|---|---|---|
| IF-SFTAttack=TokenForcing-TF2026.01 | 100 | |
| Chain&HashAttack=TokenForcing-TF2026.01 | 50 | |
| KinGuardAttack=TokenForcing-TF2026.01 | 0 |
| Method | Links | |
|---|---|---|
| IF-SFTAttack=TokenForcing-TF2026.01 | 100 | |
| Chain&HashAttack=TokenForcing-TF2026.01 | 50 | |
| KinGuardAttack=TokenForcing-TF2026.01 | 0 |