Malicious Prompt Detection on Llama-2 7B-Chat (GCG Attacks)
100Detection AccuracyJoPA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| JoPABackbone=Llama-2 (7B-Chat), Targeted Attack=GCG2024.05 | 100 | 3 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| JoPABackbone=Llama-2 (7B-Chat), Targeted Attack=GCG2024.05 | 100 | 3 |