# Preprint reports 97% accuracy classifying software supply chain threats

_Published Friday, October 16, 2026 at 3:57 AM EDT · Security, AI, Science · Latest · Tier 2 — Notable_

Researchers report 97% accuracy and 97% macro F1 for a GPT-4 framework that classifies open-source software supply chain threats into five attack categories. Their preprint uses 999 verified incidents spanning 2018 to 2026 across eight package ecosystems.

The framework structures prompts around a defined attack taxonomy. Comparisons included eight other methods; a simple TF-IDF classifier achieved 82.3%, exceeding the tested fine-tuned Llama and SecRoBERTa models. The researchers have made their dataset, scripts and code publicly available on GitHub. The evaluation concerns classification of documented incidents.

## Sources

- [cs.CR updates on arXiv.org](https://arxiv.org/abs/2610.01263)

---
Canonical: https://techandbusiness.org/newswire/iRuZ5VvUZFrS22jCZMWdoA
Published: 2026-10-16T07:57:29.610Z
Story chronology: 2026-10-16T04:00:00.000Z
Retrieved: 2026-10-16T10:23:46.866Z
Publisher: Tech & Business (techandbusiness.org)