Prompt Injection and Jailbreak Detection on VPI
100RecallWARD-0.8b
Evaluation results
| Method | Links | |
|---|---|---|
| WARD-0.8bModel Category=Ours2026.05 | 100 | |
| GPT-5.4Model Category=Closed-source API2026.05 | 84.97 | |
| WebAgentGuard-8bModel Category=Guard model (Prompt Injection)2026.05 | 78.1 |