# elastic/ember

Elastic Malware Benchmark for Empowering Researchers

Repository: https://github.com/elastic/ember
Canonical: https://ross.abutalabs.com/products/ember
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-11-22T20:36:57+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3066, "days_push": 649, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1169, forks 314 (observed 2026-08-28T04:03:51.125106+00:00)

## What it is
EMBER is a benchmark dataset of features extracted from over 2 million PE (Portable Executable) files for training and evaluating malware classification models. The repository includes tooling to reproducibly extract features from PE files, train benchmark models, and classify new files.

## Use cases
- train a malware classifier on PE file features
- benchmark machine learning models for malware detection
- extract static features from Windows executables
- research the evolution of PE file features over time
- classify new PE files with pretrained benchmark models
- build a dataset for security research on executables

## When to choose
- you need a large labeled dataset of PE files for malware research
- you want reproducible feature extraction from executables
- you need a standard benchmark to compare malware detection models

## When to avoid
- you need dynamic or behavioral malware analysis features
- you need real-time malware detection in production
- you work on macOS, where consistent feature extraction is not verified

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, security, data-science
- domain: machine-learning, security
- platform: python, windows
- tags: malware-detection, pe-files, benchmark-dataset, feature-extraction, static-analysis, security-research, malware-analysis, linux

## Member repositories
- elastic/ember (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:51.125106+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:28:41.286305+00:00, confidence not recorded.
  - readme: https://github.com/elastic/ember (fetched 2026-08-28T04:03:51.125106+00:00, sha f37fc111c19e)
- Data as of 2026-08-30T08:39:29.467469+00:00.