Rerouting Detection on D (test)
100AccuracyRerouteGuard
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RerouteGuardAttack Scenario=Gray-box2026.01 | 100 | 100 | |
| RerouteGuardAttack Scenario=Box-free2026.01 | 100 | 100 | |
| RerouteGuardAttack Scenario=White-box2026.01 | 100 | 100 | |
| RerouteGuardAttack Scenario=Average2026.01 | 100 | 100 | |
| PPLAttack Scenario=White-box2026.01 | 87 | 87 | |
| PPLAttack Scenario=Gray-box2026.01 | 74 | 71 | |
| PPLAttack Scenario=Average2026.01 | 68 | 53 | |
| LlamaGuardAttack Scenario=Gray-box2026.01 | 52 | 52 | |
| LlamaGuardAttack Scenario=White-box2026.01 | 52 | 52 | |
| LlamaGuardAttack Scenario=Average2026.01 | 51 | 52 | |
| PromptGuardAttack Scenario=Box-free2026.01 | 50 | 67 | |
| PromptGuardAttack Scenario=Gray-box2026.01 | 49 | 65 | |
| LlamaGuardAttack Scenario=Box-free2026.01 | 49 | 50 | |
| PromptGuardAttack Scenario=Average2026.01 | 48 | 64 | |
| PromptGuardAttack Scenario=White-box2026.01 | 45 | 61 | |
| PPLAttack Scenario=Box-free2026.01 | 43 | 0 |