Data Steal on Ship
95.9ASRTIP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TIPDefense=Instruction Prevention2026.03 | 95.9 | 40 | |
| TIPDefense=No Defense2026.03 | 95 | 60 | |
| TIPDefense=Perplexity Filtering2026.03 | 93 | 440 | |
| TIPDefense=Finetuned Detector2026.03 | 68.2 | 2,560 | |
| TIPDefense=Sandwich Prevention2026.03 | 49 | 1,780 | |
| TAPDefense=Perplexity Filtering2026.03 | 27.1 | 2,580 | |
| FixedDefense=Perplexity Filtering2026.03 | 1.2 | — | |
| FixedDefense=No Defense2026.03 | 0 | — | |
| TAPDefense=No Defense2026.03 | 0 | 2,580 | |
| FixedDefense=Instruction Prevention2026.03 | 0 | — | |
| TAPDefense=Instruction Prevention2026.03 | 0 | 2,520 | |
| FixedDefense=Sandwich Prevention2026.03 | 0 | — | |
| TAPDefense=Sandwich Prevention2026.03 | 0 | 2,580 | |
| FixedDefense=Finetuned Detector2026.03 | 0 | — | |
| TAPDefense=Finetuned Detector2026.03 | 0 | 2,580 |