Prompt Injection Defense on Indirect Prompt Injection Tail 1.0
0.11ASR NaiveExtraction removal method
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Extraction removal methodModel=Llama3-8b-Instruct, Defense=Extraction2025.02 | 0.11 | 1 | 0.11 | 1.77 | 3.44 | |
| StruQModel=Llama3.1-8b-Instruct, Defense=StruQ2025.02 | 0.11 | 4.77 | 4.33 | 86.22 | 79.33 | |
| Extraction removal methodModel=Llama3.1-8b-Instruct, Defense=Extraction2025.02 | 0.11 | 1.22 | 0.11 | 2.11 | 3.77 | |
| Extraction removal methodModel=Qwen2-7b-Instruct, Defense=Extraction2025.02 | 0.22 | 0.22 | 0.33 | 2.44 | 4.22 | |
| StruQModel=Llama3-8b-Instruct, Defense=StruQ2025.02 | 0.66 | 2.55 | 10.55 | 75.33 | 72 | |
| Segmentation removal methodModel=Qwen2-7b-Instruct, Defense=Segment2025.02 | 0.77 | 0.11 | 0.77 | 16.88 | 0.11 | |
| Segmentation removal methodModel=Llama3-8b-Instruct, Defense=Segment2025.02 | 3.11 | 0.11 | 3.11 | 14.44 | 0.11 | |
| StruQModel=Qwen2-7b-Instruct, Defense=StruQ2025.02 | 4.22 | 1.22 | 6.44 | 94.55 | 84.66 | |
| Segmentation removal methodModel=Llama3.1-8b-Instruct, Defense=Segment2025.02 | 5.88 | 0.11 | 5.88 | 14.88 | 0.11 | |
| SandwichModel=Llama3-8b-Instruct, Defense=Sandwich2025.02 | 10.88 | 16.11 | 25.77 | 12.11 | 14.77 | |
| SandwichModel=Llama3.1-8b-Instruct, Defense=Sandwich2025.02 | 13 | 17.88 | 22.33 | 18.33 | 24.44 | |
| SandwichModel=Qwen2-7b-Instruct, Defense=Sandwich2025.02 | 24 | 29.66 | 27.11 | 54.11 | 57.22 | |
| InstructionalModel=Llama3-8b-Instruct, Defense=Instructional2025.02 | 39.11 | 51.33 | 64.33 | 64.88 | 65 | |
| InstructionalModel=Qwen2-7b-Instruct, Defense=Instructional2025.02 | 41.22 | 55.33 | 59.88 | 95.66 | 88 | |
| NoneModel=Llama3-8b-Instruct, Defense=None2025.02 | 46.88 | 69.22 | 69.22 | 75.77 | 83 | |
| NoneModel=Qwen2-7b-Instruct, Defense=None2025.02 | 47.44 | 63.33 | 65.66 | 96.44 | 93.66 | |
| InstructionalModel=Llama3.1-8b-Instruct, Defense=Instructional2025.02 | 52.77 | 58.55 | 63.66 | 73.66 | 80 | |
| NoneModel=Llama3.1-8b-Instruct, Defense=None2025.02 | 63.77 | 76.11 | 75.44 | 85.44 | 86.11 |