1
MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation
专为多方计算（MPC）打造的安全感知LLM代码补丁基准，评估大模型生成补丁的安全性。
arXiv:2606.11416v1 Announce Type: cross Abstract: Repository-level benchmarks for evaluating Large Language Model (LLM) code repair on Secure Multi-Pa…