Adversarial Robustness Evaluation on OpenBookQA (QA)
100Attack Success Rate (ASR)CacheTrap
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CacheTrapModel=LLaMA-2-7B, Target Class=02025.11 | 100 | 80 | |
| CacheTrapModel=LLaMA-2-7B, Target Class=12025.11 | 100 | — | |
| CacheTrapModel=LLaMA-2-7B, Target Class=22025.11 | 100 | — | |
| CacheTrapModel=LLaMA-2-7B, Target Class=32025.11 | 100 | — | |
| CacheTrapModel=LLaMA-3.1-8B, Target Class=02025.11 | 100 | 87.8 | |
| CacheTrapModel=LLaMA-3.1-8B, Target Class=12025.11 | 100 | — | |
| CacheTrapModel=LLaMA-3.1-8B, Target Class=22025.11 | 100 | — | |
| CacheTrapModel=LLaMA-3.1-8B, Target Class=32025.11 | 100 | — | |
| CacheTrapModel=Mistral-7B, Target Class=02025.11 | 100 | 85.6 | |
| CacheTrapModel=Mistral-7B, Target Class=12025.11 | 100 | — | |
| CacheTrapModel=Mistral-7B, Target Class=22025.11 | 100 | — | |
| CacheTrapModel=Qwen-2.5-3B, Target Class=02025.11 | 100 | 86 | |
| CacheTrapModel=Qwen-2.5-3B, Target Class=12025.11 | 100 | — | |
| CacheTrapModel=Qwen-2.5-3B, Target Class=22025.11 | 100 | — | |
| CacheTrapModel=Qwen-2.5-3B, Target Class=32025.11 | 100 | — | |
| CacheTrapModel=DeepSeek-7B, Target Class=02025.11 | 100 | 75.2 | |
| CacheTrapModel=DeepSeek-7B, Target Class=12025.11 | 100 | — | |
| CacheTrapModel=DeepSeek-7B, Target Class=22025.11 | 100 | — | |
| CacheTrapModel=DeepSeek-7B, Target Class=32025.11 | 100 | — | |
| CacheTrapModel=Mistral-7B, Target Class=32025.11 | 99.2 | — |