[KongchangAI]
Model

jTrans

A baseline model for binary code similarity detection that achieves 0.9740 ROC-AUC on the TREX benchmark.

Timeline (last 90 days)

Nov 10

MicroSim significantly outperforms baseline models on the TREX benchmark: Gemini (0.9332 ROC-AUC), SAFE (0.9752), jTrans (0.9740), and the Bag-of-Words baseline (0.9484).

Unverified50%

All Facts (1)

Source Articles