Reproduce “A Hybrid Approach for Automated Security Pattern Recovery” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Anh Minh Nguyen, Tuan Dat Tran, Alzubair Hassan, Liliana Pasquale
SecPatRec recovers security-pattern roles and interaction sequences by using an LLM to locate role implementations, then tracing calls among mapped entities in a code property graph (CPG). Across 100 instances and four LLMs, mean role detection accuracy (RDA), mapping localization score (MLS), and interaction recovery correctness (IRC) were 0.84, 0.84, and 0.66; results cover five patterns in Java and Python.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.