POLYFLOW: A Neuro-Symbolic Framework for Static Cross-Language Information Flow Analysis
PolyFlow is a neural-symbolic framework for statically reasoning about information flow across language boundaries, combining large language models (LLMs) and static analysis synergistically, and is cost-effective and superior to various kinds of state-of-the-art baselines.
Haoran Yang, Zhi-Xuan Zhong, Jiawei Guo et al.
· 0 citations