Detection Accuracy on c4 subset
100AccuracyMC2MARK
Evaluation Results
| Method | Links | |
|---|---|---|
| MC2MARKmessage_length=16, base_model=Phi-3.5-mini-instruct2026.02 | 100 | |
| MC2MARKmessage_length=32, base_model=Phi-3.5-mini-instruct2026.02 | 100 | |
| MC2MARKmessage_length=64, base_model=Phi-3.5-mini-instruct2026.02 | 99.03 | |
| MC2MARKmessage_length=128, base_model=Phi-3.5-mini-instruct2026.02 | 98.8 | |
| BiMarkmessage_length=16, base_model=Phi-3.5-mini-instruct2026.02 | 98.19 | |
| MPAC(1.5)message_length=16, base_model=Phi-3.5-mini-instruct2026.02 | 95.19 | |
| MC2MARKmessage_length=256, base_model=Phi-3.5-mini-instruct2026.02 | 93.95 | |
| BiMarkmessage_length=32, base_model=Phi-3.5-mini-instruct2026.02 | 93.47 | |
| MC2MARKmessage_length=512, base_model=Phi-3.5-mini-instruct2026.02 | 90.16 | |
| BiMarkmessage_length=64, base_model=Phi-3.5-mini-instruct2026.02 | 86.19 | |
| MPAC(1.0)message_length=16, base_model=Phi-3.5-mini-instruct2026.02 | 85.5 | |
| MPAC(1.5)message_length=32, base_model=Phi-3.5-mini-instruct2026.02 | 84.34 | |
| MPAC(1.5)message_length=64, base_model=Phi-3.5-mini-instruct2026.02 | 76.44 | |
| MPAC(1.0)message_length=32, base_model=Phi-3.5-mini-instruct2026.02 | 74.31 | |
| BiMarkmessage_length=128, base_model=Phi-3.5-mini-instruct2026.02 | 73.28 | |
| MPAC(1.5)message_length=128, base_model=Phi-3.5-mini-instruct2026.02 | 70.74 | |
| MPAC(1.0)message_length=64, base_model=Phi-3.5-mini-instruct2026.02 | 70 | |
| MPAC(1.5)message_length=256, base_model=Phi-3.5-mini-instruct2026.02 | 63.16 | |
| MPAC(1.0)message_length=128, base_model=Phi-3.5-mini-instruct2026.02 | 60.82 | |
| MPAC(1.5)message_length=512, base_model=Phi-3.5-mini-instruct2026.02 | 58.42 | |
| MPAC(1.0)message_length=256, base_model=Phi-3.5-mini-instruct2026.02 | 58.34 | |
| MPAC(1.0)message_length=512, base_model=Phi-3.5-mini-instruct2026.02 | 56.44 | |
| BiMarkmessage_length=256, base_model=Phi-3.5-mini-instruct2026.02 | 55.28 | |
| BiMarkmessage_length=512, base_model=Phi-3.5-mini-instruct2026.02 | 36.15 |