Benign Utility on ACIARENA Code 1.0 (test)
66.67BUAutoGen + SANDWICH
Evaluation Results
| Method | Links | |
|---|---|---|
| AutoGen + SANDWICHMAS Platform=AutoGen, Defense=SANDWICH2026.04 | 66.67 | |
| AgentVerse + SANDWICHMAS Platform=AgentVerse, Defense=SANDWICH2026.04 | 66.67 | |
| AgentVerse + DELIMITERMAS Platform=AgentVerse, Defense=DELIMITER2026.04 | 63.33 | |
| AgentVerse + ACI-SENTINELMAS Platform=AgentVerse, Defense=ACI-SENTINEL2026.04 | 62.22 | |
| AgentVerse + BERT DETECTORMAS Platform=AgentVerse, Defense=BERT DETECTOR2026.04 | 61.11 | |
| AgentVerseMAS Platform=AgentVerse, Defense=None2026.04 | 60 | |
| AutoGenMAS Platform=AutoGen, Defense=None2026.04 | 57.78 | |
| MetaGPTMAS Platform=MetaGPT, Defense=None2026.04 | 57.78 | |
| AutoGen + DELIMITERMAS Platform=AutoGen, Defense=DELIMITER2026.04 | 55.56 | |
| AgentVerse + AGRAILMAS Platform=AgentVerse, Defense=AGRAIL2026.04 | 54.44 | |
| AutoGen + ACI-SENTINELMAS Platform=AutoGen, Defense=ACI-SENTINEL2026.04 | 52.22 | |
| MetaGPT + SANDWICHMAS Platform=MetaGPT, Defense=SANDWICH2026.04 | 51.11 | |
| AgentVerse + G-SAFEGUARDMAS Platform=AgentVerse, Defense=G-SAFEGUARD2026.04 | 46.67 | |
| AutoGen + BERT DETECTORMAS Platform=AutoGen, Defense=BERT DETECTOR2026.04 | 45.56 | |
| MetaGPT + ACI-SENTINELMAS Platform=MetaGPT, Defense=ACI-SENTINEL2026.04 | 44.44 | |
| AutoGen + G-SAFEGUARDMAS Platform=AutoGen, Defense=G-SAFEGUARD2026.04 | 40 | |
| AutoGen + AGRAILMAS Platform=AutoGen, Defense=AGRAIL2026.04 | 32.22 | |
| MetaGPT + G-SAFEGUARDMAS Platform=MetaGPT, Defense=G-SAFEGUARD2026.04 | 31.11 | |
| MetaGPT + BERT DETECTORMAS Platform=MetaGPT, Defense=BERT DETECTOR2026.04 | 25.56 | |
| MetaGPT + DELIMITERMAS Platform=MetaGPT, Defense=DELIMITER2026.04 | 18.89 | |
| MetaGPT + AGRAILMAS Platform=MetaGPT, Defense=AGRAIL2026.04 | 6.67 |