Reproduce “Benchmarking Unsupervised Jamming Detection in 5G Open RAN” 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
Sneihil Gopal, Fernando J. Cintron, Richard A. Rouil
The authors introduce a composite score to compare unsupervised jamming detectors by mapping outputs to alarm masks and confidence values. It combines confidence on flagged samples with alarm-interval continuity, though confidence signals have different meanings across detectors. Across ten leave-one-out testbed traces, SEM leads AEs in composite score (0.906 versus 0.688) and F1 (0.918 versus 0.521). The score can mislead under severe under-detection.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.