Reproduce “Quo Vadis: Hybrid Machine Learning Meta-Model based on Contextual and Behavioral Malware Representations” 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
Dmitrijs Trizna
Quo Vadis combines static executable features, filepaths, and emulated Windows API-call sequences to detect malware in 32-bit Windows executables. Separate models encode each view, and a meta-model combines their representations for a decision. On a test set collected three months later, the hybrid detected 86.28% of malware at 100 false positives per 100,000 cases, versus 56.86% for Ember FFNN alone.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.